TY - GEN
T1 - Understanding the Role of Weather Data for Earth Surface Forecasting using a ConvLSTM-based Model
AU - Diaconu, Codrut Andrei
AU - Saha, Sudipan
AU - Gunnemann, Stephan
AU - Xiang Zhu, Xiao
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Climate change is perhaps the biggest single threat to humankind and the environment, as it severely impacts our terrestrial surface, home to most of the living species. Inspired by video prediction and exploiting the availability of Copernicus Sentinel-2 images, recent studies have attempted to forecast the land surface evolution as a function of past land surface evolution, elevation, and weather. Further extending this paradigm, we propose a model based on convolutional long short-term memory (ConvLSTM) that is computationally efficient (lightweight), however obtains superior results to the previous baselines. By introducing a ConvLSTM-based architecture to this problem, we can not only ingest the heterogeneous data sources (Sentinel-2 time-series, weather data, and a Digital Elevation Model (DEM)) but also explicitly condition the future predictions on the weather. Our experiments confirm the importance of weather parameters in understanding the land cover dynamics and show that weather maps are significantly more important than the DEM in this task. Furthermore, we perform generative simulations to investigate how varying a single weather parameter can alter the evolution of the land surface. All studies are performed using the EarthNet2021 dataset. The code, additional materials and results can be found at https://github.com/dcodrut/weather2land.
AB - Climate change is perhaps the biggest single threat to humankind and the environment, as it severely impacts our terrestrial surface, home to most of the living species. Inspired by video prediction and exploiting the availability of Copernicus Sentinel-2 images, recent studies have attempted to forecast the land surface evolution as a function of past land surface evolution, elevation, and weather. Further extending this paradigm, we propose a model based on convolutional long short-term memory (ConvLSTM) that is computationally efficient (lightweight), however obtains superior results to the previous baselines. By introducing a ConvLSTM-based architecture to this problem, we can not only ingest the heterogeneous data sources (Sentinel-2 time-series, weather data, and a Digital Elevation Model (DEM)) but also explicitly condition the future predictions on the weather. Our experiments confirm the importance of weather parameters in understanding the land cover dynamics and show that weather maps are significantly more important than the DEM in this task. Furthermore, we perform generative simulations to investigate how varying a single weather parameter can alter the evolution of the land surface. All studies are performed using the EarthNet2021 dataset. The code, additional materials and results can be found at https://github.com/dcodrut/weather2land.
UR - http://www.scopus.com/inward/record.url?scp=85137776746&partnerID=8YFLogxK
U2 - 10.1109/CVPRW56347.2022.00142
DO - 10.1109/CVPRW56347.2022.00142
M3 - Conference contribution
AN - SCOPUS:85137776746
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1361
EP - 1370
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
PB - IEEE Computer Society
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Y2 - 19 June 2022 through 20 June 2022
ER -