Deep learning for vegetation health forecasting: A case study in Kenya
East Africa has experienced a number of devastating droughts in recent decades, including the 2010/2011 drought. The National Drought Management Authority in Kenya relies on real-time information from MODIS satellites to monitor and respond to emerging drought conditions in the arid and semi-arid la...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
MDPI
2022
|
| _version_ | 1797106892598673408 |
|---|---|
| author | Lees, T Tseng, G Atzberger, C Reece, S Dadson, S |
| author_facet | Lees, T Tseng, G Atzberger, C Reece, S Dadson, S |
| author_sort | Lees, T |
| collection | OXFORD |
| description | East Africa has experienced a number of devastating droughts in recent decades, including the 2010/2011 drought. The National Drought Management Authority in Kenya relies on real-time information from MODIS satellites to monitor and respond to emerging drought conditions in the arid and semi-arid lands of Kenya. Providing accurate and timely information on vegetation conditions and health—and its probable near-term future evolution—is essential for minimising the risk of drought conditions evolving into disasters as the country’s herders directly rely on the conditions of grasslands. Methods from the field of machine learning are increasingly being used in hydrology, meteorology, and climatology. One particular method that has shown promise for rainfall-runoff modelling is the Long Short Term Memory (LSTM) network. In this study, we seek to test two LSTM architectures for vegetation health forecasting. We find that these models provide sufficiently accurate forecasts to be useful for drought monitoring and forecasting purposes, showing competitive performances with lower resolution ensemble methods and improved performances over a shallow neural network and a persistence baseline. |
| first_indexed | 2024-03-07T07:07:27Z |
| format | Journal article |
| id | oxford-uuid:38e51b6b-4029-4f6e-8d8b-ae9fb8309950 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:07:27Z |
| publishDate | 2022 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oxford-uuid:38e51b6b-4029-4f6e-8d8b-ae9fb83099502022-05-24T06:50:02ZDeep learning for vegetation health forecasting: A case study in KenyaJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:38e51b6b-4029-4f6e-8d8b-ae9fb8309950EnglishSymplectic ElementsMDPI2022Lees, TTseng, GAtzberger, CReece, SDadson, SEast Africa has experienced a number of devastating droughts in recent decades, including the 2010/2011 drought. The National Drought Management Authority in Kenya relies on real-time information from MODIS satellites to monitor and respond to emerging drought conditions in the arid and semi-arid lands of Kenya. Providing accurate and timely information on vegetation conditions and health—and its probable near-term future evolution—is essential for minimising the risk of drought conditions evolving into disasters as the country’s herders directly rely on the conditions of grasslands. Methods from the field of machine learning are increasingly being used in hydrology, meteorology, and climatology. One particular method that has shown promise for rainfall-runoff modelling is the Long Short Term Memory (LSTM) network. In this study, we seek to test two LSTM architectures for vegetation health forecasting. We find that these models provide sufficiently accurate forecasts to be useful for drought monitoring and forecasting purposes, showing competitive performances with lower resolution ensemble methods and improved performances over a shallow neural network and a persistence baseline. |
| spellingShingle | Lees, T Tseng, G Atzberger, C Reece, S Dadson, S Deep learning for vegetation health forecasting: A case study in Kenya |
| title | Deep learning for vegetation health forecasting: A case study in Kenya |
| title_full | Deep learning for vegetation health forecasting: A case study in Kenya |
| title_fullStr | Deep learning for vegetation health forecasting: A case study in Kenya |
| title_full_unstemmed | Deep learning for vegetation health forecasting: A case study in Kenya |
| title_short | Deep learning for vegetation health forecasting: A case study in Kenya |
| title_sort | deep learning for vegetation health forecasting a case study in kenya |
| work_keys_str_mv | AT leest deeplearningforvegetationhealthforecastingacasestudyinkenya AT tsengg deeplearningforvegetationhealthforecastingacasestudyinkenya AT atzbergerc deeplearningforvegetationhealthforecastingacasestudyinkenya AT reeces deeplearningforvegetationhealthforecastingacasestudyinkenya AT dadsons deeplearningforvegetationhealthforecastingacasestudyinkenya |