Interview with Linda See
This is a modal window.
The media could not be loaded, either because the server or network failed or because the format is not supported.
Formal Metadata
| Title |
| |
| Title of Series | ||
| Number of Parts | 44 | |
| Author | ||
| Contributors | ||
| License | CC Attribution 3.0 Germany: You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. | |
| Identifiers | 10.5446/66863 (DOI) | |
| Publisher | ||
| Release Date | ||
| Language | ||
| Producer | ||
| Production Year | 2024 | |
| Production Place | Wageningen |
Content Metadata
| Subject Area | ||
| Genre | ||
| Abstract |
| |
| Keywords |
8
9
10
11
15
17
19
22
23
25
27
29
32
36
37
41
00:05
Musical ensembleVertex (graph theory)Principal idealMeeting/Interview
00:10
AlgorithmoutputProcess modelingMultiplication signInterpreter (computing)Visualization (computer graphics)Game controllerExpert systemPresentation of a groupReference dataCovering spaceSeries (mathematics)Data qualityStandard deviationArithmetic meanSet (mathematics)SatelliteGoodness of fitInteractive televisionDifferent (Kate Ryan album)Maxima and minimaImage resolutionMappingMaterialization (paranormal)BitWave packetMeeting/Interview
Transcript: English(auto-generated)
00:09
So my name is Linda C. I also work at IASA in the nodes research group and I'm principal research scholar I've been working at IASA since 2010. I gave a brief overview of GeoWiki
00:22
Which has been developed at IASA for reference data collection using crowdsourcing and citizen science So at the start I sort of described the motivation for how GeoWiki developed And I gave a summary of the different crowdsourcing campaigns that we've run over the last decade I then explained the kinds of tools that are in GeoWiki that aid the crowd and visual interpretation of satellite imagery
00:44
And then I finished with a bit of ongoing research including some of the new and exciting developments in in GeoWiki So really one of the main motivations for me is improving maps of land cover and land use So there's been a huge increase in the amount of satellite imagery available, higher spatial resolution, higher temporal resolution
01:05
But the challenge continues to be lack of reference data So my main motivation has been to try to increase the amount of reference data available to improve remote sensing algorithms Because ultimately I'd like to see the world mapped more accurately so that the models that use the data
01:21
Have the best possible inputs for assessing policy, environmental impacts, etc. Well, there's many but okay Well, I think one of the key challenges is ensuring data quality and we have a few different approaches for handling this I didn't have time to talk about this during the presentation But so for example before we run a data collection campaign We put together what we call an expert or a control data set
01:43
So there are a series of known answers to the visual interpretation and then we provide this to the crowd during the campaign But we do it randomly So the users don't know when they're going to get one of these Expert or control data sets and we penalize the users if they make mistakes Which sounds a bit mean but it's a way of ensuring that we keep up the quality
02:03
Okay So if they know that there's a chance that they could be penalized then and they don't know when it's going to happen They keep up the quality. So we also require a certain standard or a minimum data quality to Before we give up prizes, for example, so it's not just about collecting as much data as possible
02:23
It's collecting a lot of data, but high quality data So that's another way Okay, other challenges include just running the campaigns, you know, they're quite an intensive An intensive process and they require a lot of interaction between us and the crowd We need to create good
02:42
Training materials and I think we've gotten a lot better at that over time So that so that the crowd learns and they also get better at visual interpretation over time So those are just some of the challenges, but there's actually many