NASA ARSET Data Analysis and Visualization

0:03 Speaker 1: Welcome back to our r SET training series Advanced NASA

0:08 Speaker 1: Earth Observations and Tools for Active fire, smoke and post

0:12 Speaker 1: fire monitoring. Today is part two of our training series.

0:16 Speaker 1: My name is Brock Blevins, a training coordinator for the

0:19 Speaker 1: r SET program, and I'll be your host for today's training.

0:24 Speaker 1: As I mentioned in Part two, or the final part

0:27 Speaker 1: of this training series, we will have an overview of

0:31 Speaker 1: static thermal anomaly data inside firms, how to use static

0:36 Speaker 1: thermal anomaly information to identify thermal anomalies that are not

0:40 Speaker 1: likely vegetation fires, how to visualize active fire information on

0:46 Speaker 1: static graphs and interactive maps, and how to analyze active

0:51 Speaker 1: fire information using a fire count histogram. Once again, the

0:58 Speaker 1: homework is available now on the training web page. It

1:02 Speaker 1: will be due December third, and a certificate of completion

1:07 Speaker 1: will be awarded to those who attend both five sessions

1:10 Speaker 1: and complete the homework by December third. And with that

1:15 Speaker 1: let's begin Part two of the training series, Data Analysis

1:19 Speaker 1: and Visualization. I'm very happy to introduce our guest instructors

1:24 Speaker 1: for Part two. Brad Quail joins us from the US

1:27 Speaker 1: Forest Service where he is the lead for the Disturbance

1:32 Speaker 1: Assessment and Services program, and we also have Dylan Mendez,

1:36 Speaker 1: a senior application developer for Firms.

1:40 Speaker 2: Part objectives.

1:42 Speaker 1: By the end of part two, we hope that participants

1:44 Speaker 1: will be able to recognize how static thermal anomalies associated

1:48 Speaker 1: with industrial and natural sources are identified, use data available

1:55 Speaker 1: in firms to identify locations of routinely detected static thermae

2:00 Speaker 1: WILL anomalies, and use Jupiter notebooks to access and visualized

2:04 Speaker 1: firms data. Once again, if you have any questions during

2:10 Speaker 1: today's training, you can put them in the Q and

2:12 Speaker 1: A box within WebEx at any time. At the end

2:15 Speaker 1: of this training, we'll address as many questions as we can,

2:18 Speaker 1: and then we'll post a transcript of these questions and

2:21 Speaker 1: written and answers to the training web page within a week.

2:27 Speaker 2: Let's get right to it.

2:28 Speaker 1: First demonstration by Brad will be on static thermal anomalies.

2:36 Speaker 2: In particular. His outline will.

2:38 Speaker 1: Show an overview of static thermal anomaly data available in firms,

2:43 Speaker 1: accessing STA data, associated data and tools in firms, and

2:48 Speaker 1: how to use firms to highlight examples of thermal anomaly

2:51 Speaker 1: activity they are not likely vegetation.

2:54 Speaker 2: Fire over to you, Brad. Thank you.

3:03 Speaker 3: All right, thank you. Well.

3:04 Speaker 4: Today, what I'm going to demonstrate is our new static

3:07 Speaker 4: thermal nominally data that we've incorporated firms, along with some

3:10 Speaker 4: associated data sets and tools we've included to use those data.

3:15 Speaker 4: And what you see here as a firm's map of

3:17 Speaker 4: Oregon and western Idaho. And I'm going to zoom in

3:19 Speaker 4: here to northeast Oregon to a little town called the

3:23 Speaker 4: Dirky Organ And as you can see, if I zoom

3:26 Speaker 4: into this location here, just outside that town, there's a

3:30 Speaker 4: large excavated area with an associated area of industrial infrastructure

3:37 Speaker 4: here and this particular area, if I turn on the

3:42 Speaker 4: fire detections, I can see I'm getting some detection activity

3:46 Speaker 4: associated with that infrastructure next to the excavation pit. Well,

3:50 Speaker 4: this area here is a cement plant. And this is

3:54 Speaker 4: a really good example of a static thermal anomaly feature

3:58 Speaker 4: because sment plants have large kilns that they use to

4:02 Speaker 4: heat up material to make cement. And these kilns burn

4:06 Speaker 4: at very high temperatures or have very high temperatures approaching

4:08 Speaker 4: fifteen hundred degrees centigrade. And these features can be detected

4:14 Speaker 4: by satellites and included an active fire detection data, and

4:17 Speaker 4: that's why we can see them here. If I back

4:21 Speaker 4: off a little bit here on the scale, you can

4:23 Speaker 4: see those features and here's some other detected activity here,

4:27 Speaker 4: likely associated with a fire. But if I jump ahead

4:31 Speaker 4: one month to the end of July of twenty twenty four,

4:35 Speaker 4: again looking back thirty one days in the active fire

4:39 Speaker 4: detection record, I have all these other fire detections that

4:43 Speaker 4: are associated with wildland fire activity that was occurring at

4:46 Speaker 4: that time. And as you can see as those detection

4:50 Speaker 4: data fill in, I have a lot of detections for

4:53 Speaker 4: the month of July for that cement plant we just

4:55 Speaker 4: looked at before. Now, if you're a wildland fire manager,

4:59 Speaker 4: you may that may give you pauseing you'd wonder if

5:02 Speaker 4: you're not familiar with the area that might be associated

5:05 Speaker 4: that detection activity might be associated with the wild land fire.

5:10 Speaker 4: So having these static thermal anomaly features inventory and identified

5:16 Speaker 4: allows users to identify these areas of fire detections that

5:21 Speaker 4: might be associated with industrial features or natural features that

5:25 Speaker 4: are giving off heat or thermal activity and can be

5:30 Speaker 4: detected in active fire detection products. So static thermal anomalies

5:37 Speaker 4: what are they In the context of firms. They're basically

5:40 Speaker 4: semi persistent or persistent sources of thermal energy that we

5:45 Speaker 4: can detect routinely in active fire detection products. But they're

5:49 Speaker 4: not vegetation fires. They're associated with industrial features or industrial activity,

5:55 Speaker 4: and in some cases they can be associated with natural

5:58 Speaker 4: features that they're given up heat, such as volcanos and

6:01 Speaker 4: other sources of geneo thermal activity. And what we did

6:07 Speaker 4: in developing this static thermal anomaly feature or layer that

6:11 Speaker 4: is in firms right now is we started with year

6:14 Speaker 4: twenty twenty three cumulative active fire detection data that was

6:17 Speaker 4: acquired by SMPP bears. It is about twenty one million

6:21 Speaker 4: active fire detections worldwide, and then we also included terra

6:26 Speaker 4: and aqua active fire detections for the same year, which

6:30 Speaker 4: was an additional eight million. So we had about twenty

6:32 Speaker 4: nine million active fire detection data that we processed and

6:35 Speaker 4: analyzed and thresholded accordingly, and we summarized those data and

6:41 Speaker 4: we identified features that we determined were static emitters of

6:48 Speaker 4: thermal energy, and we identified well over sixty three hundred

6:51 Speaker 4: of them and they're represented here on this map. So

6:58 Speaker 4: the next thing I'm going to show is we're going

6:59 Speaker 4: to jump to a map in firms for Western Turkey,

7:03 Speaker 4: and what if you want to access the static Thermal

7:07 Speaker 4: Anomalies layer mask, it's under this Static Thermal Anomalies group

7:13 Speaker 4: in firms and you can see I have it drawn

7:16 Speaker 4: up and you can they're very small features at this scale,

7:21 Speaker 4: and they're they're showing up in magenta. But if I

7:24 Speaker 4: change my background layer to a dark gray, they stand

7:27 Speaker 4: out a lot better. You can see them here throughout

7:29 Speaker 4: Turkey and a decrease and whatnot.

7:33 Speaker 3: We also have.

7:36 Speaker 4: Sources of industrial heat or industrial activity identified. Now we

7:42 Speaker 4: didn't develop this these layers in firms, but we went

7:47 Speaker 4: to authoritative sources who inventory and compile this data globally,

7:52 Speaker 4: and we've provided these data and firms for reference. So

7:56 Speaker 4: we have all types of different industrial plants and also

8:00 Speaker 4: power plants which may be emitters of heat. And so

8:03 Speaker 4: if I turn on a couple of these layers here

8:06 Speaker 4: you can see these iron and steel plants, cement plants

8:10 Speaker 4: and so forth. And if I go to the layer

8:14 Speaker 4: info for one of those layers, you get a brief

8:17 Speaker 4: description of what this layer enteils, and you also have

8:21 Speaker 4: a citation, a link to get to the source data

8:27 Speaker 4: if you'd like, and also a citation for the data layer.

8:31 Speaker 4: If you have any questions about these layers, we recommend

8:34 Speaker 4: that you contact the authoritative sources for these data because

8:38 Speaker 4: these data, again are not developed by NASA. They come

8:40 Speaker 4: from these various sources and we're just provide them here

8:43 Speaker 4: as a courtesy in firms for folks to have contexts

8:45 Speaker 4: and reference to these data. So I'm going to switch

8:50 Speaker 4: back to the image base and I'm going to zoom

8:54 Speaker 4: in here on this town in Turkey called Heroes the Turkey,

9:00 Speaker 4: and I've turned on the static thermal anomalies mask and

9:04 Speaker 4: magenta there and you can see that this area corresponds

9:09 Speaker 4: to an industrial area there on the coast. And if

9:13 Speaker 4: I turn on the fire detections for this day, I'm

9:16 Speaker 4: looking at June twenty sixth, at twenty twenty five, and

9:18 Speaker 4: I'm just I have a one day reach back, so

9:20 Speaker 4: we're just looking for the detections that occurred on this day.

9:25 Speaker 4: You can see that there is a fire that's burning

9:29 Speaker 4: in this forested area to the south of town, and

9:31 Speaker 4: we're also picking up thermal activities associated with the static

9:35 Speaker 4: thermal anomaly area. Well, what we've done in firms is

9:39 Speaker 4: provided the capability to filter and identify active fire detections

9:44 Speaker 4: that are associated with the static thermal anomalies layers or features,

9:49 Speaker 4: I should say. And under the static thermalomalies group, there's

9:52 Speaker 4: a static thermal anomalies detection layer, and if I turn

9:55 Speaker 4: that on in Cyan, these detections that are I that

10:00 Speaker 4: correspond or that are associated with the static thermal anomalies

10:03 Speaker 4: feature will be highlighted. And basically what it's doing is

10:07 Speaker 4: features that directly intersect the static thermal anomaly area as

10:11 Speaker 4: well as or within a pre defined buffer tolerance are selected,

10:15 Speaker 4: so we can see that these detections are associated with

10:20 Speaker 4: the industrial activity here. And we're picking up a little

10:23 Speaker 4: bit here that some detections that are associated with that fire,

10:27 Speaker 4: but that's due to the buffer tolerance we're using there.

10:29 Speaker 4: We try not to get too aggressive so we don't

10:31 Speaker 4: pick up detections too far outside of the static thermal

10:35 Speaker 4: anomaly feature. If I jump ahead one day, this fire

10:40 Speaker 4: started the day before, you can see again for that

10:43 Speaker 4: day on the twenty fifth, here's all they have fire

10:45 Speaker 4: activity associated with that forest fire south of the city,

10:50 Speaker 4: and these are the active fire detections associated with that

10:54 Speaker 4: static thermal anomaly feature. Just want to note here you

10:58 Speaker 4: noticed on the previous day, and today we have some

11:00 Speaker 4: detections in this area. This is obviously of industrial origin,

11:08 Speaker 4: these active fire detections, but we our static thermal anomaly

11:11 Speaker 4: feature does not extend out there and capture that. And

11:14 Speaker 4: that's because again for this initial prototype layer we have,

11:19 Speaker 4: we did not We only used that you know, year

11:21 Speaker 4: twenty twenty three active fire detections and so we just

11:24 Speaker 4: didn't have any detected activity in that area. That meant

11:28 Speaker 4: our thresholds and criteria to identify that as a static

11:31 Speaker 4: thermal anomaly. So just you know, for little things that

11:35 Speaker 4: are nuances like that for users to be aware of

11:37 Speaker 4: when they're using these static thermal anomaly features. For the

11:46 Speaker 4: next part of my demo, I'm going to jump to

11:48 Speaker 4: the Hues Fire, which was a fire that burned in

11:51 Speaker 4: southern California in January twenty twenty five. And what I'm

11:55 Speaker 4: looking at here is on the date of January twenty eighth,

11:59 Speaker 4: reaching back for one week, all the cumulative active fire

12:02 Speaker 4: detections for modus and vehers that occurred with this fire.

12:07 Speaker 4: And as you can see here, we have a little

12:10 Speaker 4: cluster of detections here a couple kilometers away from the

12:14 Speaker 4: fire that's associated with this excavated barren area. And what

12:19 Speaker 4: this area is here is it's a landfill area. And

12:24 Speaker 4: I zoom in here on it a little bit and

12:26 Speaker 4: turn off the detections. You can see that area and

12:32 Speaker 4: what it looks like up close there. But I'm gonna

12:34 Speaker 4: zoom back out and turn the detections back on. And

12:39 Speaker 4: if I turn on my static thermal anomalies layer, but

12:45 Speaker 4: that render there is a little bit slow displaying and

12:48 Speaker 4: you can see those magenta That magenta polygon is that

12:53 Speaker 4: our static thermal anomalies mass that was derived from the

12:56 Speaker 4: twenty twenty three active fire detection data. So what is

13:01 Speaker 4: going on here is upon doing a little bit of

13:03 Speaker 4: research in this area, this is a landfill that in

13:08 Speaker 4: twenty twenty two basically an underground fire started there. So

13:14 Speaker 4: the garbage and the waste that's been buried there in

13:18 Speaker 4: that landfill was ignited and the fire has been burning

13:22 Speaker 4: underground and smoldering and whatnot for the last three years.

13:25 Speaker 4: And this thermal activities routinely detected by the active fire

13:31 Speaker 4: detection sources in firms. So having this information would you know,

13:37 Speaker 4: possibly help a fire manager to know that these fire

13:40 Speaker 4: detections that are close to the you know, the Hues

13:42 Speaker 4: fire when it was going on. They are not associated

13:46 Speaker 4: with that incident. But as you can see as I

13:49 Speaker 4: jump through time here and maybe if I jump into February,

13:55 Speaker 4: well after the Hues fire was over, we're still picking

13:59 Speaker 4: up these detections three times. So just to show you

14:02 Speaker 4: that that you know, relatively small, subtle smoldering thermal activity

14:07 Speaker 4: that's happening there with that landfill fire is being picked

14:12 Speaker 4: up and detected. And of course I can turn on

14:14 Speaker 4: my static thermal anomalies detections and isolate those detections with

14:20 Speaker 4: that activity if I'm interested in doing so. On this

14:26 Speaker 4: last example of working with static thermal anomaly data, we're

14:30 Speaker 4: going to focus on a natural heat source. And where

14:35 Speaker 4: I'm at right now with this map is this map.

14:38 Speaker 4: It shows the East African Rift Valley and you can

14:41 Speaker 4: see here we have a couple of volcanoes that are

14:44 Speaker 4: present and where we have some active fire detections that

14:47 Speaker 4: are occurring with those volcanoes. And this area here in

14:51 Speaker 4: general is the Democratic Republic of Congo. And to identify

14:57 Speaker 4: where these volcanoes are at, if you look under the overla,

15:00 Speaker 4: we have a volcano layer, and you can filter these

15:03 Speaker 4: volcanoes for what's displayed based on their most recent activity.

15:10 Speaker 4: We have here by default on those volcanoes have been

15:13 Speaker 4: active in the last sixty years are displayed, but if

15:15 Speaker 4: I toggle it to display all of them, you can

15:18 Speaker 4: see we have all these other dormant volcanoes that have

15:21 Speaker 4: not also erupted in the past sixty years. So I'm

15:27 Speaker 4: going to toggle that back to just the ones that

15:29 Speaker 4: have been active in the last sixty years, and I'm

15:31 Speaker 4: going to zoom in on this volcano here. It's called Nayamalazra,

15:35 Speaker 4: and this is the most active volcano in Africa. And

15:39 Speaker 4: as you can see on this particular date for July thirtieth,

15:42 Speaker 4: with a one day reach back for the active fire

15:44 Speaker 4: detection data, we have a lot of active fire detections

15:47 Speaker 4: that are associated with the volcanic activity that's occurring on

15:52 Speaker 4: this volcano that day. And if I draw the static

15:56 Speaker 4: thermal anomalies layer and turn off my active fire detections

15:59 Speaker 4: from moment, you can see the static thermal anomaly feature

16:04 Speaker 4: that we discerned using the twenty twenty three active fire

16:07 Speaker 4: detection data is pretty pretty large. It extends about three

16:10 Speaker 4: to four kilometers from the main crater of the volcano,

16:14 Speaker 4: and if I turn my detections back on from Modus

16:17 Speaker 4: and Beers for this day, both the day and night detections,

16:21 Speaker 4: and if I turn on my static thermal anomalies detections,

16:24 Speaker 4: I can easily filter and identify those active ore detections

16:29 Speaker 4: that are associated with the static thermal anomaly feature. But

16:32 Speaker 4: I'm going to turn that out for a moment, and

16:34 Speaker 4: also the static thermal anomaly's mask, and I'm going to

16:37 Speaker 4: turn off all of the active fire detection layers except

16:41 Speaker 4: for the Noah twenty one beers data for that day,

16:45 Speaker 4: and I'm also going to turn off the night time detection,

16:48 Speaker 4: so we're just looking at the daytime detections associated with

16:51 Speaker 4: the volcanic activity. And if I turn off the volcano

16:56 Speaker 4: layer here so you can see it a little bit easier,

16:58 Speaker 4: you can see these are the detection is right here

17:01 Speaker 4: on the volcano, on the volcano itself that we got

17:05 Speaker 4: some activity there, but we also have some activity here

17:07 Speaker 4: off the west slope as well as trending down the

17:10 Speaker 4: east slope of the volcano. So if I look at

17:15 Speaker 4: the Noah twenty one beer's false color composite imagery on

17:19 Speaker 4: this day and turn off my active fire detections.

17:23 Speaker 3: For a moment.

17:25 Speaker 4: Again, this is relatively coarse resolution imagery at this scale,

17:28 Speaker 4: but you can see with the shortwave in for red response,

17:31 Speaker 4: we have some thermal activity going on here in faint

17:34 Speaker 4: that you can see some thermal activity out here far

17:36 Speaker 4: on the west, on the west slope as well. I'm

17:39 Speaker 4: going to turn my beer's active fire detection back on

17:43 Speaker 4: and also turn off my Beer's imagery, and I'm going

17:47 Speaker 4: to take a look at the HLS imagery and it

17:50 Speaker 4: happens on this particular day, July thirtieth, both lands At

17:54 Speaker 4: and Sentinel to imagery were acquired for the area. And

17:59 Speaker 4: if I drop up the true composite imagery, this is

18:01 Speaker 4: what it looks like on that day, the Sentinel imagery.

18:05 Speaker 4: And now I'm going to draw the false color composite

18:09 Speaker 4: imagery for the Sentinel to acquisition. Here it comes in

18:17 Speaker 4: for patients here. As it draws in again, it repeating

18:21 Speaker 4: me some of what we learned with the working with

18:24 Speaker 4: the HLS data before. The true color composite imagery draws

18:27 Speaker 4: in very fast, but the false color composite imagery is

18:31 Speaker 4: rendered a little bit slower than the true color composite imagery.

18:38 Speaker 4: And if we take a look close look at this imagery.

18:44 Speaker 4: If we take a close look at this imagery in

18:46 Speaker 4: the context of the active fire detection data from BEERS,

18:50 Speaker 4: you can see with the if I turn off the

18:53 Speaker 4: active fire detection data, I have all these areas that

18:57 Speaker 4: are easily visible in the short wave in forread data

19:00 Speaker 4: that are resulting from the thermal activity, the lava and

19:04 Speaker 4: the eruption activity that's going on around the part of

19:08 Speaker 4: the volcano here, and it's coming down the east slope

19:11 Speaker 4: as well as all this activity that's easily seen in

19:15 Speaker 4: coming down the west slope. So these are lava flows

19:18 Speaker 4: coming down from the main crater of the volcano, and

19:21 Speaker 4: so that's what we're seeing when we see those detections

19:24 Speaker 4: farther out to the west and also creeping down the

19:27 Speaker 4: east slope. And this is a good example of how

19:31 Speaker 4: you can use the HLS imagery, which is much higher

19:34 Speaker 4: spatial resolution than the Veers and Motus imagery to discern

19:40 Speaker 4: and determine maybe what is going on there on the

19:42 Speaker 4: ground and is the source of the thermal.

19:45 Speaker 3: Detected activity that you can see there.

19:48 Speaker 4: This wraps up my demonstration here today with the stat

19:52 Speaker 4: of thermalomaly data, and I just wanted to say again

19:55 Speaker 4: that this current stat of thermal anomaly layer that we

19:58 Speaker 4: have in firms is a prototype layer. It needs more

20:02 Speaker 4: work and improvements and the firm's team is working on

20:05 Speaker 4: doing that and we plan to release an updated static

20:09 Speaker 4: thermal anomalies layer in the future.

20:12 Speaker 3: Thank you.

20:19 Speaker 1: Thank you very much Brad for that thorough demonstration of

20:23 Speaker 1: static thermal anomaly data and firms and its functionalities.

20:27 Speaker 2: It was great to get a tour of how to

20:29 Speaker 2: use it.

20:32 Speaker 1: In this next demonstration, Dylan will be showing us how

20:35 Speaker 1: to generate a firm's map key, how to visualize active

20:38 Speaker 1: fire information on a static graph and interactive map, and

20:43 Speaker 1: how to analyze that fire data. If we would like

20:46 Speaker 1: to replicate the demonstration provided by Dylan, please see the

20:50 Speaker 1: link to the GitHub which can be found under part

20:53 Speaker 1: two of our training web page, as well as a

20:56 Speaker 1: link and how to generate a map key. We'll make

20:59 Speaker 1: a record of this demonstration available by tomorrow so you

21:03 Speaker 1: can go through the process at your own pace.

21:11 Speaker 5: Amazing well, thank you for the more technical part of

21:16 Speaker 5: this training. Here is where your start for the coding portion,

21:25 Speaker 5: and this is a gub repository. There should have been

21:29 Speaker 5: more materials provided if you'd like to check out how

21:32 Speaker 5: it works and all, but it's pretty simple. First you

21:35 Speaker 5: all need to go to the firm's website here get

21:40 Speaker 5: an API key. When you come over here, you'll just

21:43 Speaker 5: click get map key, put in your information and click

21:46 Speaker 5: get map key. You'll then get an email where the

21:50 Speaker 5: body looks something like this. This is just a demonstration

21:53 Speaker 5: key for the webinars to what we do. But you'll

21:56 Speaker 5: take this key right up here at the top and

21:58 Speaker 5: that will be your MAP key that you will need

22:00 Speaker 5: to use the notebook that is linked down here. To

22:04 Speaker 5: get to the notebook, all you have to do is

22:06 Speaker 5: hit open an colab here. This will take you over

22:10 Speaker 5: to Google co lab and then you'll be able to

22:14 Speaker 5: make a copy and then do some work from there.

22:18 Speaker 5: So I'll take my.

22:21 Speaker 3: API key.

22:22 Speaker 2: There's some.

22:24 Speaker 5: API overview information and different information on our sources and

22:31 Speaker 5: all the different satellites that are available. But the code

22:34 Speaker 5: starts down here in the setup and authentication part. And

22:39 Speaker 5: then you will take your API key and where this

22:42 Speaker 5: big green bar is you put it in between these

22:45 Speaker 5: two quotes. Once you've done that this will enable. You'll

22:52 Speaker 5: click run and then this will ask you if you're

22:55 Speaker 5: connect if you'd like to connect to Google. They can't

22:58 Speaker 5: from GitHub, so you can click run anyway. After that

23:04 Speaker 5: is done, it will connect to some server provided by

23:07 Speaker 5: Google and it will import all of these packages that

23:11 Speaker 5: are used in this training and you'll see setup complete.

23:17 Speaker 5: API key is loaded. Then we can come down here

23:22 Speaker 5: to the world example. This function I wrote to query

23:26 Speaker 5: the firm's API for the world with all of the

23:31 Speaker 5: information on the different sources, day range, daystring, all of

23:35 Speaker 5: the things like that. Pick play just to load this function.

23:40 Speaker 5: Once you load this function, you can pass the details

23:44 Speaker 5: into it, and we're looking at the world here for

23:46 Speaker 5: the date of August twentieth, in twenty twenty five for

23:50 Speaker 5: the VIAS NOAH twenty nearal time.

23:55 Speaker 3: Data sise.

24:02 Speaker 5: It'll print out exactly what a FI link you used here.

24:05 Speaker 5: You can click on that and then it'll bring you

24:07 Speaker 5: into a new tab with the raw data itself. But

24:12 Speaker 5: this will load the data into a data frame from

24:17 Speaker 5: PANDACE and you can see an example of the first

24:21 Speaker 5: couple of lines here. The information included below there is

24:26 Speaker 5: all of these columns and this little backslash is showing

24:30 Speaker 5: me that it's continued on the next line. So these

24:32 Speaker 5: are the rest of the columns, and now I'll move

24:38 Speaker 5: on to showing you a bounding box example. Only to

24:44 Speaker 5: run this to load the function so that it can

24:48 Speaker 5: be called in the next block. This bounding box is

24:53 Speaker 5: in the Amazon basin and I prepared it ahead of

24:56 Speaker 5: time just so that everyone could get a quick example.

25:01 Speaker 5: Once you run this, it will show you the data

25:04 Speaker 5: Bougust twenty six, twenty twenty five for the data inside

25:10 Speaker 5: the bounding box, and then it will also print out

25:14 Speaker 5: an example of the data frame here, which is similar

25:18 Speaker 5: to the one above for the world. In this case

25:22 Speaker 5: we're using the Veers SNPP satellite in the new real time.

25:30 Speaker 5: These are our available sources below with information on their

25:36 Speaker 5: real time status standard status where they cover in the

25:40 Speaker 5: case of Landsat. And that just shows you how to

25:45 Speaker 5: get the data in a bounding box and a function

25:47 Speaker 5: to use that to pass the bounding box and to

25:54 Speaker 5: ingest the data into a geo data frame from the

25:59 Speaker 5: firmas with lat long coordinates. Will run this function that

26:04 Speaker 5: turns it into a geo data frame and we can

26:09 Speaker 5: run the data on the data frame area from the

26:15 Speaker 5: world example, which is up here labeled data frame area.

26:22 Speaker 5: This will take in that data frame area and then

26:24 Speaker 5: turn it into a geo data frame as an example

26:31 Speaker 5: shown here with the points. You can do an exercise

26:37 Speaker 5: here to see how do some continue to do some

26:41 Speaker 5: coding and see the amount of the number of points

26:46 Speaker 5: or active fire detections in this example with the confidence

26:50 Speaker 5: above eighty, you can easily filter on the confidence which

26:57 Speaker 5: does not look like there's one on the Beer's s

27:00 Speaker 5: PP satellite. But manipulating the function up here or a

27:07 Speaker 5: different source or calling it in. When you call the

27:12 Speaker 5: function itself, we'll be able to reveal some different confidence

27:16 Speaker 5: values that are not available for all of our satellites

27:19 Speaker 5: for various reasons. So that we can view some of

27:23 Speaker 5: these satellite detections, We're going to use the geodata frame

27:29 Speaker 5: and then a function in that so that we can

27:33 Speaker 5: show these active fire detections in the world for the

27:38 Speaker 5: same date of August twentieth plus one day, so there's

27:43 Speaker 5: two days total. Once we run this, it will show

27:49 Speaker 5: the exact thing loot that we were showing earlier, showing

27:54 Speaker 5: the world and you can kind of make out Africa

27:56 Speaker 5: over here and North America into South America over here, and.

28:00 Speaker 2: Europe and Asia over here.

28:04 Speaker 3: This will.

28:06 Speaker 5: This is a static plot, so you can't zoom in

28:10 Speaker 5: or click into it. However, we can use the folio

28:12 Speaker 5: map to show the same data on a interactive map

28:20 Speaker 5: so that we are able to zoom in and such

28:23 Speaker 5: and see different areas. In this case, it's colored by confidence.

28:32 Speaker 5: It's taking a little bit to run.

28:34 Speaker 3: Right now.

28:44 Speaker 5: Now that it's been executing, we can scroll in the

28:48 Speaker 5: bottom box below the code and see the different parts

28:52 Speaker 5: of the map. We can zoom in or out send

28:55 Speaker 5: that backwards and take a look at the different fire

29:00 Speaker 5: detections based on confidence, and we can go to part

29:04 Speaker 5: of Brazil over here and see that it is colored

29:07 Speaker 5: in a way.

29:08 Speaker 3: That we wanted it to be.

29:15 Speaker 2: All right, We.

29:20 Speaker 5: Will now count fires by the day, so, using the

29:26 Speaker 5: same data frame earlier on the acquisition date variable, we

29:32 Speaker 5: will convert into daytime and then create some grouped by

29:35 Speaker 5: date time or group by the acquisition date, and then

29:38 Speaker 5: the size of those acquisition dates, so it will be

29:40 Speaker 5: the number of fire detections by the acquisition date. And

29:46 Speaker 5: then we can use PLT to plot the figure. Right now,

29:50 Speaker 5: it's only showing one day go up and show let's

30:04 Speaker 5: go change this to two days. We will now do

30:18 Speaker 5: some manipulation based on the date, and you can do

30:21 Speaker 5: this for any of the different columns that are available

30:26 Speaker 5: in our output, or additional data that you have brought

30:29 Speaker 5: in to do some subsetting or some charts on. Right now,

30:36 Speaker 5: we're going to take the data frame the acquisition date.

30:39 Speaker 5: We're going to turn it into a daytime objects that

30:42 Speaker 5: I can be grouped by the date, and the size

30:46 Speaker 5: in this case is the number of fire counts. I

30:49 Speaker 5: just showed this earlier, but now you can see that

30:53 Speaker 5: I went from one day to two days worth the

30:56 Speaker 5: data of August twentieth and August twenty first, showing that

30:59 Speaker 5: there were more fires on or more active fire detections

31:04 Speaker 5: on August twenty first in the world and there was

31:06 Speaker 5: on August twenty As a conclusion, we set up authentication

31:14 Speaker 5: for the firm's API, retrieve data using the firms API

31:18 Speaker 5: and bounding box queries, and for the world. I ingested

31:23 Speaker 5: the data into PANDAS and GEOPANDAE, visualized the fire detections

31:27 Speaker 5: with the static and interactive maps, and then analyze some

31:30 Speaker 5: temporal patterns. That is just some basic manipulation of our

31:36 Speaker 5: firms active fire detections using our API. You can expand

31:42 Speaker 5: this to historical trends over time, overlaying fire detections with

31:47 Speaker 5: different information that you may have about various things that

31:53 Speaker 5: have to do with lands such as land cover or

31:56 Speaker 5: population data sets. And you can also developed automated monitoring

32:00 Speaker 5: pipelines from things like this. Below is the homework section

32:05 Speaker 5: which is where you'll be able to do all the

32:07 Speaker 5: homework here below. And yeah, that's it for me. Thank

32:13 Speaker 5: you all for watching.

32:21 Speaker 1: Great, Thank you very much, Dylan, And as I mentioned,

32:24 Speaker 1: we're going to make this recording available by tomorrow so

32:27 Speaker 1: you can go through this on your own time. But

32:30 Speaker 1: let's summarize what we learned here today. First, Brad showed

32:36 Speaker 1: us how to access and use stas and firms, which

32:40 Speaker 1: included the display of STA layers, a display of the

32:44 Speaker 1: STA feature source types such as industrial heat sources or

32:48 Speaker 1: natural heat sources, and identify active fire detections associated with STS.

32:54 Speaker 1: And we also saw how to access and just and

32:56 Speaker 1: visualize first day using the super or notebook. And just

33:02 Speaker 1: to summarize this training series, this two part training demonstrating

33:07 Speaker 1: two participants several new capabilities. Within firms. In Part one,

33:12 Speaker 1: we looked at burned area mode in firms new veers,

33:15 Speaker 1: burned area product and the use of HLS imagery and

33:19 Speaker 1: indices to perform burned area assessments. This is useful as

33:23 Speaker 1: monitoring post fire impacts of vegetation is essential for evaluating

33:27 Speaker 1: burned severity, which informs post fire de brief flow risk,

33:31 Speaker 1: understanding patterns of ecosystem recovery, and identifying areas required for

33:36 Speaker 1: restoration intervention. We also looked at smoke and aerosol mode

33:41 Speaker 1: in firms, the use of aerosol index and PYROCB layers

33:45 Speaker 1: to identify and track wildfire smoke and as we learned

33:50 Speaker 1: while fare, smoke monitoring is critical for air quality and

33:52 Speaker 1: public health applications as exposure to find particular matter within

33:57 Speaker 1: smoke can cause respiratory issues and other health complications. And

34:01 Speaker 1: then in part two today we looked at static thermal

34:04 Speaker 1: anomaly information to identify satellite active fire detections that may

34:08 Speaker 1: be associated with industrial courses and then also how to

34:12 Speaker 1: access ingest, visualize, and manipulate firms data using a Jupiter notebook.

34:20 Speaker 2: Homework is available now on the training webpage.

34:22 Speaker 1: It'll be due on the third of December, and for

34:27 Speaker 1: those who did book live webinars and completed the homework

34:30 Speaker 1: by the deadline, you will receive a certificate of completion

34:33 Speaker 1: the email approximately two months after the completion.

34:37 Speaker 2: Of this course.

34:40 Speaker 1: Here we've included the contact information for myself and today's speakers,

34:44 Speaker 1: as well as links to our set website and YouTube channel.

34:51 Speaker 1: I would like to take another opportunity to acknowledge our

34:53 Speaker 1: fantastic guest presenters Jenny Houston, Brad Quail, Dyln Mendez, Diane Davies,

35:01 Speaker 1: as well as as and Radoff and Upmar Belsina from

35:04 Speaker 1: the firm's team. Thank you very much for joining us

35:10 Speaker 1: on this training series. And now we'll move over to

35:14 Speaker 1: the question and answer session. We've been monitoring the Q

35:23 Speaker 1: and A box for questions and we've been moving them

35:27 Speaker 1: over to this document. If you have future questions, please

35:30 Speaker 1: locate the three little dots on the lower right hand

35:33 Speaker 1: side of the application or web browser.

35:38 Speaker 2: For this WebEx and you'll see a Q and A section.

35:41 Speaker 1: Please answer your questions there, but the ones that we

35:43 Speaker 1: have we've tried to start answering, so we can start

35:47 Speaker 1: off with question number one.

35:52 Speaker 2: What are the data we rely on for fire detections.

35:55 Speaker 2: Is it only thermal.

35:56 Speaker 1: Data or smoke or is there any other data that

35:58 Speaker 1: helps fire false positives like wind congestion or accuracy metrics.

36:07 Speaker 1: I think I got the gist of what this question

36:11 Speaker 1: was asking.

36:13 Speaker 3: Hey brod this Brad. I can take that question.

36:15 Speaker 2: Oh, hey Brad, great dear, Yeah.

36:18 Speaker 3: Yeah, great question. Yeah.

36:20 Speaker 4: The way the active fire detection works it's it's reliable

36:24 Speaker 4: or it's reliant on thermal data or thermal detection of activity,

36:29 Speaker 4: and it can be affected by a heavy cloud cover,

36:33 Speaker 4: heavy smoke cover, as is noted in response here. And

36:36 Speaker 4: the way it works is, uh, you know, when it

36:38 Speaker 4: identifies obvious uh, you know, thermal activity, you know, above

36:43 Speaker 4: average temperatures there and a big given pixel, what it

36:47 Speaker 4: does is it slides into what we call a contextual

36:49 Speaker 4: analysis part of the algorithm, and it looks at neighboring

36:53 Speaker 4: or adjacent pixels to assess their thermal response in order

36:57 Speaker 4: to figure out what that pixel would look like in

37:00 Speaker 4: the absence of fire. And if we have a large

37:02 Speaker 4: enough departure, there's statistically from that thermal response based on

37:06 Speaker 4: the response of its neighbors which are not also obvious fires,

37:11 Speaker 4: the algorithm can then determine with a certain level of

37:15 Speaker 4: confidence whether or not that's an active fire detection or not.

37:18 Speaker 4: And the second part of your question, you know, as

37:20 Speaker 4: far as using information that can help you identify if

37:23 Speaker 4: there's you know, potential false positives on a detection, you

37:26 Speaker 4: can use the confidence information that I mentioned, Like on

37:31 Speaker 4: the Modus active fire detections, there's a confidence a level

37:35 Speaker 4: that ranges between zero and one hundred percent, and with

37:39 Speaker 4: the veer's data, it's a categorical rating of low, moderate,

37:46 Speaker 4: or high confidence and that those confidence levels are affected

37:53 Speaker 4: by you know, where the detection is, like if it's

37:55 Speaker 4: adjacent to a water body or a cloud edge or whatnot,

37:58 Speaker 4: which may cause some confusion in the thermal response and

38:02 Speaker 4: determining the.

38:03 Speaker 3: Statistics that I mentioned before.

38:05 Speaker 4: So you could look at those confidence levels for an

38:09 Speaker 4: active fire detection and maybe you know, consider excluding some

38:13 Speaker 4: of those very low confidence level detections which may be

38:18 Speaker 4: actual false positives.

38:21 Speaker 1: Great, thank you, and I put the link that you

38:24 Speaker 1: see right here to the firm facts in the chest.

38:28 Speaker 1: Question number two, how about aerosol layer this is it

38:31 Speaker 1: possible to estimate spatial distribution? Have we ever use other

38:35 Speaker 1: satellites like Tempo or paste to integrate into the results.

38:42 Speaker 2: I brock, this is Jenny, and I can take that one.

38:46 Speaker 6: So Firms currently makes available aerosol index layers from AMPS

38:53 Speaker 6: which is about smpp as well as NOWHA twenty and

38:57 Speaker 6: this was covered last week by Diane Webinar one. This particular,

39:04 Speaker 6: this set of aerosols index layers are useful for both

39:09 Speaker 6: both the detection as well as the tracking of aerosols

39:12 Speaker 6: and aerosols from from smoke from fires as well as

39:17 Speaker 6: interestingly dust storms. And I also wanted to highlight the

39:23 Speaker 6: NASA's overarching near real time system, which is called LAMPS

39:29 Speaker 6: and within which the Firm system is situated, continually investigates

39:35 Speaker 6: additional data sources that could be useful for a range

39:38 Speaker 6: of applications, including wildfires for example, and has recently made

39:44 Speaker 6: available multiple near real time products from Essay's Triponi sensor,

39:50 Speaker 6: including an aerosol index product, as well as selected neural

39:57 Speaker 6: products from PACE. And we are currently working to make

40:02 Speaker 6: available selected near real time tempo questions which I know

40:08 Speaker 6: that the question has specifically asked about, so I will

40:13 Speaker 6: provide the links for those as well for the PACE on.

40:19 Speaker 2: Thank you, Thank you very much.

40:22 Speaker 1: Yeah, so it sounds like you are already on top

40:25 Speaker 1: of a lot of this other data being integrated.

40:29 Speaker 2: Question three, what is the definition of data ingestion?

40:32 Speaker 1: And I think this was asding Dylan's demonstration near the end.

40:39 Speaker 2: Yeah, and the answer here just a means of acquiring

40:43 Speaker 2: the data.

40:45 Speaker 3: Yeah.

40:46 Speaker 1: If there's a follow up question from that participant, please

40:49 Speaker 1: please let us know if there's more that you wanted

40:51 Speaker 1: to know. For another question, is it possible that firms

40:55 Speaker 1: captures temperature anomalies caused by other sources rather than fire?

40:58 Speaker 1: I saw areas on the map, I know, and suffer

41:02 Speaker 1: from urban heat islands by high levels of infermeable surfaces

41:07 Speaker 1: such as asphalt or buildings.

41:14 Speaker 4: Yeah, Brock, Brock here, I'm happy to take that. Yeah,

41:17 Speaker 4: that that's another really good question.

41:20 Speaker 3: Yeah.

41:20 Speaker 4: The fire detect algorithms are used for you know, modus

41:22 Speaker 4: and bears and you know the other sensors are available

41:25 Speaker 4: uh in in in firms. Uh. They're they're designed to

41:30 Speaker 4: detect and measure uh thermal radiation that you know, are

41:35 Speaker 4: at very elevated or high uh temperatures that are associated

41:39 Speaker 4: with you know, combustion and fire and whatnot. So uh,

41:43 Speaker 4: these types of you know, thermal anomalies that you're describing

41:47 Speaker 4: here with urban heat islands and whatnot. They're they're there's

41:50 Speaker 4: there's not designed to uh, you know, detect activity at

41:53 Speaker 4: that particular temperature and whatnot. In some cases, you know,

41:57 Speaker 4: in some sensors, you know, particular a should I say

42:03 Speaker 4: it's approaches have ad to be taken to exclude those

42:06 Speaker 4: areas so we don't end up getting false positives all

42:08 Speaker 4: over the place, like from urban heat islands and you know,

42:11 Speaker 4: desert surfaces and whatnot. But yeah, the algorithms are designed

42:15 Speaker 4: to not capture those areas as thermal anomalies.

42:24 Speaker 2: Great, thank you very much, Brad.

42:26 Speaker 1: It sounds like, yeah, the sensors aren't just designed for

42:29 Speaker 1: that particular detection.

42:32 Speaker 2: Question five. I was wondering if the static.

42:34 Speaker 1: Thermal anomaly masks we saw on the firm's website are

42:37 Speaker 1: made available somewhere as shape files. I would be interested

42:42 Speaker 1: to use them from through the mass I use to

42:44 Speaker 1: distinguish vegetation fires from non vegetation fires in my own algorithm.

42:51 Speaker 2: And it looks like there's a start of an answer here.

42:55 Speaker 5: Yeah, so I can take that one. So we do

42:57 Speaker 5: not distribute the static thermal MoMA later. But the information tab,

43:02 Speaker 5: the little I icon on the firm's website gives you

43:06 Speaker 5: all the information about where we are getting our static

43:10 Speaker 5: thermo anomalies information from.

43:16 Speaker 2: Okay, thank you very much. Question number six, what sort

43:25 Speaker 2: of time intervals? For sure? With the WRT?

43:31 Speaker 1: I guess what kind of temporal resolution or flower vacations

43:35 Speaker 1: are are you working with your data? And I'm going

43:37 Speaker 1: to assume this is going to vary depending on what

43:40 Speaker 1: centsor platform we're talking about.

43:44 Speaker 5: Yeah, I can take that. There are various temporal sampling

43:53 Speaker 5: based on the satellite you're looking at. It's different for

43:55 Speaker 5: modus and different for beers, different VI GEO stationary satellite,

44:00 Speaker 5: it's all across the world. Our frequently asked questions would

44:04 Speaker 5: be the best place to find information about that or

44:06 Speaker 5: in the information tab on whatever layer you're looking at.

44:13 Speaker 2: Okay, great, thank you very much.

44:14 Speaker 1: So I'm the layer and then you can find some

44:16 Speaker 1: information on how often that is being sampled, thank you.

44:23 Speaker 3: Yeah.

44:23 Speaker 5: And one more note in our advanced mode, I think

44:27 Speaker 5: is where it is there is orbit overpasses up the

44:33 Speaker 5: polar orbiting satellite, so notice and yours that can help

44:38 Speaker 5: you identify when the satellite has overpassed your area or

44:42 Speaker 5: area of interest.

44:44 Speaker 2: Oh great, thanks for pointing that out.

44:45 Speaker 1: If I remember correctly, the intro to firms earlier this

44:49 Speaker 1: year had a section where that was being displayed. Okay,

44:56 Speaker 1: I have a question. I haven't moved over here yet,

44:58 Speaker 1: but I'm going to throw it in here so everybody

45:04 Speaker 1: can see it. What about solar farms? Is it possible

45:10 Speaker 1: that they will show a map like a false positive?

45:18 Speaker 4: Yeah, Brad, here, I can take that one, Brock, Yes,

45:22 Speaker 4: potentially solar farms. Can you know due to sun glint

45:27 Speaker 4: cause false positives in various active fire detection products? These

45:32 Speaker 4: polar urbaning active fire detection products, like for motus and beers,

45:37 Speaker 4: the NASA algorithms are very robust. You know.

45:40 Speaker 3: They use additional bands.

45:43 Speaker 4: In the in the visible and neurinfrared wavelengths to help

45:47 Speaker 4: identify those areas of sun glint and reject those false positives.

45:51 Speaker 4: So the the beers and Modus data are pretty good

45:55 Speaker 4: in rejecting or keeping.

45:57 Speaker 3: Those false positives out of the the data.

46:00 Speaker 4: However, the geostationary active our detection algorithms are are not

46:07 Speaker 4: as quite as good as motus and fairs in rejecting

46:12 Speaker 4: those identifying and rejecting those false positives, so you would

46:16 Speaker 4: have a tendency to see those false positives from sun

46:19 Speaker 4: glint from solid farms showing up in the geostationary active

46:22 Speaker 4: fire detection data.

46:27 Speaker 2: Thank you.

46:30 Speaker 1: I have another question here, what what what STA detect

46:38 Speaker 1: peat fire in context of a below ground peat fire

46:43 Speaker 1: and would it be obscure by heavy smoke from vegetation fire.

46:53 Speaker 4: Yeah, I'll take that one again, Brock. The short answer

46:56 Speaker 4: would be generally, no, we're trying to exclude these natural

47:03 Speaker 4: fire events or you know, vegetation fires from the STA,

47:07 Speaker 4: and you know, we're doing that by looking at persistence

47:11 Speaker 4: of the fire activity. For example, you know, an industrial

47:15 Speaker 4: source that would have detections you know, over a long

47:19 Speaker 4: period of time throughout the year, whereas you know a

47:21 Speaker 4: wildfire you know, pete fire or whatnot would not be it,

47:26 Speaker 4: you know, persistent throughout the year. So we're trying to

47:30 Speaker 4: you know, exclude those areas wildfires and whatnot by looking

47:35 Speaker 4: at the persistence of those detections.

47:40 Speaker 2: Great, thank you.

47:44 Speaker 1: It's like there was a question in the chat. I'm

47:47 Speaker 1: not sure what the question was, but the answer from Jenny.

47:54 Speaker 1: There's been a lot of coverage of the pollution in

47:56 Speaker 1: India and the news that uses firms. Oh, I am

48:00 Speaker 1: from India and I have a yearly problem of farm

48:03 Speaker 1: fires that can contribute to the pollution. How can we

48:06 Speaker 1: distinguish general fire from double burning through veers or other

48:10 Speaker 1: natura products?

48:15 Speaker 6: Thanks Broke. I saw that question in the chat, so

48:20 Speaker 6: I just started answering it. So interestingly, there has been

48:24 Speaker 6: a lot of coverage of the pollution in India in

48:27 Speaker 6: various news sources and terms are being used. Data from

48:32 Speaker 6: firms are being used to help inform what is happening

48:38 Speaker 6: and as far as can we distinguish general fire from

48:43 Speaker 6: strubble burning. So additional contextual information so spatial extent of

48:49 Speaker 6: the farms, etc. Could be used to further kind of

48:54 Speaker 6: refine the locations and potential sources of the fires. But

48:59 Speaker 6: these fire is that are certainly being captured by both

49:04 Speaker 6: veas about NOWER twenty SMPP and now twenty one, as

49:09 Speaker 6: well as by modis about terror and Acwan.

49:16 Speaker 2: Great, thank you very much.

49:19 Speaker 1: I did see a question regarding to the homework once again.

49:23 Speaker 1: That link can be found under part two on the

49:26 Speaker 1: training web page and it is live right now. Question

49:34 Speaker 1: number ten, how does static thermoonomaly filter out thermonomaly from

49:38 Speaker 1: industrial facilities.

49:39 Speaker 2: So it's more like, how does it work. Are they

49:42 Speaker 2: using coverage binding from the file or with the nearest

49:46 Speaker 2: nerve neighbor algorithm?

49:49 Speaker 1: Tell us a little bit more about the features.

49:54 Speaker 2: Like we have a link here, we're putting a chat.

50:00 Speaker 3: Yeah, yeah, brocc I'll be happy answer to that. Yeah.

50:03 Speaker 4: As as noted in response there, we have an earth

50:07 Speaker 4: Data article posted about the s t A and how

50:11 Speaker 4: the you know, general description of how they're derived. But

50:15 Speaker 4: as mentioned before in the demo, what we what we

50:18 Speaker 4: did is we you know, took the cumul of the

50:20 Speaker 4: factor fire detections for at least sepp veers over the

50:24 Speaker 4: course of the year and also Tara and Aqua modis.

50:27 Speaker 4: We used Modus primarily take advantage of Terra's mourning observation capabilities,

50:34 Speaker 4: and then we'd have Aqua and as mpp vers for

50:37 Speaker 4: the afternoon observations. And uh yeah, we we identified those

50:43 Speaker 4: uh persistent areas where there was persistent fire detection activity

50:50 Speaker 4: within or i should say, over you know, extended period

50:53 Speaker 4: of time again looking at that persistence measure, and we're

50:57 Speaker 4: able to you know, identify those areas or locations as

51:03 Speaker 4: static thermal anomalies which may be due to industrial heat

51:06 Speaker 4: sources or natural sources.

51:09 Speaker 3: Like volcanoes and whatnot. Like as we discussed during a demo, we.

51:15 Speaker 4: Provide the sources of industrial heat activity infirms as a

51:23 Speaker 4: reference because you know, we're we're not trying to capture

51:27 Speaker 4: all industrial sources of heat out there on a landscape.

51:31 Speaker 4: We're just trying to capture the ones that are, you know,

51:33 Speaker 4: or at least identify the ones that are routinely identified

51:36 Speaker 4: in the modus and beers active fire detection products. And

51:41 Speaker 4: that helps users, you know, identify those particular detections that

51:45 Speaker 4: are associated with those features.

51:48 Speaker 3: So yeah, that's all pretty much. Have that sound that one, Brock.

51:56 Speaker 1: Here's a question, is there a way to a de

51:59 Speaker 1: linear surfs versus atmospheric thermal energy?

52:02 Speaker 2: Up Here in Canada we have a large smoke columns.

52:05 Speaker 1: That carry lots of heat and appear to artificially inflate

52:08 Speaker 1: the size of the fire. But once the smoke subsides,

52:11 Speaker 1: their hits.

52:12 Speaker 2: Are no longer valid.

52:13 Speaker 1: It often appears in a repeating grid pattern of hits

52:17 Speaker 1: along the direction of the smoke column is heading. It

52:21 Speaker 1: looks like we're gonna get back to on that one.

52:24 Speaker 1: Look for this answer to be build in, but we're

52:27 Speaker 1: going to consult our science team and get a little

52:29 Speaker 1: bit more of an accurate answer for you here.

52:35 Speaker 6: Yeah, thanks bro, And just to note that again webinar

52:39 Speaker 6: one kind of touched on this and so that would

52:42 Speaker 6: be another source of information and as well as we

52:48 Speaker 6: will consult our science team and provide additional information.

52:55 Speaker 2: Great, thank you very much. Okay, that seems to be

53:00 Speaker 2: last question right now.

53:01 Speaker 1: We have a few minutes left before the top of

53:03 Speaker 1: the hour, so if anybody has any more questions, feel

53:09 Speaker 1: free to type them into the an A box. And

53:14 Speaker 1: as it comes to the homework, it's due by the

53:18 Speaker 1: third of December, and then it's going to take a

53:22 Speaker 1: little bit of time for us to process attendance and

53:25 Speaker 1: homework submission. So typically you can expect to see your certificate.

53:30 Speaker 2: Of completion sent you as a PDF in your email

53:34 Speaker 2: about two months after today.

53:43 Speaker 1: In the meantime, this is an advanced training that builds

53:49 Speaker 1: off of one that we did earlier this year that

53:53 Speaker 1: was offered in English and Spanish. There are plans to

53:57 Speaker 1: deliver this in Spanish as well and then your future

54:02 Speaker 1: so please look for that if there's anything any of

54:07 Speaker 1: our guest speakers want to offer in general, to the

54:11 Speaker 1: participants here today, I welcome you to do so well.

54:16 Speaker 2: Thanks Broke.

54:18 Speaker 6: I would like to say thank you to everybody for

54:22 Speaker 6: participating and we hope you found this information very useful.

54:31 Speaker 2: Well, thank you very much. It's great to be back.

54:33 Speaker 1: And we thank everybody for hanging in there with us,

54:38 Speaker 1: and look for more wildland fire training to be offered

54:41 Speaker 1: by the our SET program in the future. I have

54:45 Speaker 1: a great rest of your week, everybody.

54:46 Speaker 2: Thank you.