Explainable AI in drought forecasting. Dikshit, A. & Pradhan, B. Machine Learning with Applications, October, 2021. ![Explainable AI in drought forecasting [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Droughts are one of the disastrous natural hazards which has severe impacts on agricultural production, economy, and society. One of the critical steps for effective drought management is developing a robust forecasting model and understanding how the variables affect the model outcomes. The present study forecasts SPI-12 at a lead time of 3 months, using the Long Short-Term Memory (LSTM) model, and further interprets the spatial and temporal relationship between variables and forecasting results using SHapley Additive exPlanations (SHAP). The developed model is tested in four different regions in New South Wales (NSW), Australia. SPI-12 was computed using monthly rainfall data collected from Scientific Information for Land Owners (SILO) for 1901–2018. The model was trained from 1901–2000 and tested from 2001–2018, and the performance was measured using Coefficient of Determination (R2), Nash–SutcliffeEfficiency (NSE) and Root-Mean-Square-Error (RMSE). To understand the underlying impact of variables on the model outcomes, SHAPley values were calculated for the entire testing period and also at three different temporal ranges, which are during the Millennium Drought (2001–2010), post drought period (2011–2018) and at a seasonal scale (summer months). The comparison of the results shows a significant variation in the impact of variables on forecasting, both temporally and spatially. It also shows the need to study the model outcomes for specific regions and for a shorter duration than the entire testing period. This is a first of its study towards interpreting the forecasting model in drought studies, which could help understand the behaviour of drought variables.
@article{dikshit_explainable_2021,
title = {Explainable {AI} in drought forecasting},
issn = {2666-8270},
url = {https://www.sciencedirect.com/science/article/pii/S2666827021000967},
doi = {10.1016/j.mlwa.2021.100192},
abstract = {Droughts are one of the disastrous natural hazards which has severe impacts on agricultural production, economy, and society. One of the critical steps for effective drought management is developing a robust forecasting model and understanding how the variables affect the model outcomes. The present study forecasts SPI-12 at a lead time of 3 months, using the Long Short-Term Memory (LSTM) model, and further interprets the spatial and temporal relationship between variables and forecasting results using SHapley Additive exPlanations (SHAP). The developed model is tested in four different regions in New South Wales (NSW), Australia. SPI-12 was computed using monthly rainfall data collected from Scientific Information for Land Owners (SILO) for 1901–2018. The model was trained from 1901–2000 and tested from 2001–2018, and the performance was measured using Coefficient of Determination (R2), Nash–SutcliffeEfficiency (NSE) and Root-Mean-Square-Error (RMSE). To understand the underlying impact of variables on the model outcomes, SHAPley values were calculated for the entire testing period and also at three different temporal ranges, which are during the Millennium Drought (2001–2010), post drought period (2011–2018) and at a seasonal scale (summer months). The comparison of the results shows a significant variation in the impact of variables on forecasting, both temporally and spatially. It also shows the need to study the model outcomes for specific regions and for a shorter duration than the entire testing period. This is a first of its study towards interpreting the forecasting model in drought studies, which could help understand the behaviour of drought variables.},
language = {en},
urldate = {2021-10-25},
journal = {Machine Learning with Applications},
author = {Dikshit, Abhirup and Pradhan, Biswajeet},
month = oct,
year = {2021},
keywords = {Deep learning, Drought forecasting, Explainable AI, Standard precipitation index},
pages = {100192},
}
Downloads: 0
{"_id":"xejHak7N7RisLJoKq","bibbaseid":"dikshit-pradhan-explainableaiindroughtforecasting-2021","author_short":["Dikshit, A.","Pradhan, B."],"bibdata":{"bibtype":"article","type":"article","title":"Explainable AI in drought forecasting","issn":"2666-8270","url":"https://www.sciencedirect.com/science/article/pii/S2666827021000967","doi":"10.1016/j.mlwa.2021.100192","abstract":"Droughts are one of the disastrous natural hazards which has severe impacts on agricultural production, economy, and society. One of the critical steps for effective drought management is developing a robust forecasting model and understanding how the variables affect the model outcomes. The present study forecasts SPI-12 at a lead time of 3 months, using the Long Short-Term Memory (LSTM) model, and further interprets the spatial and temporal relationship between variables and forecasting results using SHapley Additive exPlanations (SHAP). The developed model is tested in four different regions in New South Wales (NSW), Australia. SPI-12 was computed using monthly rainfall data collected from Scientific Information for Land Owners (SILO) for 1901–2018. The model was trained from 1901–2000 and tested from 2001–2018, and the performance was measured using Coefficient of Determination (R2), Nash–SutcliffeEfficiency (NSE) and Root-Mean-Square-Error (RMSE). To understand the underlying impact of variables on the model outcomes, SHAPley values were calculated for the entire testing period and also at three different temporal ranges, which are during the Millennium Drought (2001–2010), post drought period (2011–2018) and at a seasonal scale (summer months). The comparison of the results shows a significant variation in the impact of variables on forecasting, both temporally and spatially. It also shows the need to study the model outcomes for specific regions and for a shorter duration than the entire testing period. This is a first of its study towards interpreting the forecasting model in drought studies, which could help understand the behaviour of drought variables.","language":"en","urldate":"2021-10-25","journal":"Machine Learning with Applications","author":[{"propositions":[],"lastnames":["Dikshit"],"firstnames":["Abhirup"],"suffixes":[]},{"propositions":[],"lastnames":["Pradhan"],"firstnames":["Biswajeet"],"suffixes":[]}],"month":"October","year":"2021","keywords":"Deep learning, Drought forecasting, Explainable AI, Standard precipitation index","pages":"100192","bibtex":"@article{dikshit_explainable_2021,\n\ttitle = {Explainable {AI} in drought forecasting},\n\tissn = {2666-8270},\n\turl = {https://www.sciencedirect.com/science/article/pii/S2666827021000967},\n\tdoi = {10.1016/j.mlwa.2021.100192},\n\tabstract = {Droughts are one of the disastrous natural hazards which has severe impacts on agricultural production, economy, and society. One of the critical steps for effective drought management is developing a robust forecasting model and understanding how the variables affect the model outcomes. The present study forecasts SPI-12 at a lead time of 3 months, using the Long Short-Term Memory (LSTM) model, and further interprets the spatial and temporal relationship between variables and forecasting results using SHapley Additive exPlanations (SHAP). The developed model is tested in four different regions in New South Wales (NSW), Australia. SPI-12 was computed using monthly rainfall data collected from Scientific Information for Land Owners (SILO) for 1901–2018. The model was trained from 1901–2000 and tested from 2001–2018, and the performance was measured using Coefficient of Determination (R2), Nash–SutcliffeEfficiency (NSE) and Root-Mean-Square-Error (RMSE). To understand the underlying impact of variables on the model outcomes, SHAPley values were calculated for the entire testing period and also at three different temporal ranges, which are during the Millennium Drought (2001–2010), post drought period (2011–2018) and at a seasonal scale (summer months). The comparison of the results shows a significant variation in the impact of variables on forecasting, both temporally and spatially. It also shows the need to study the model outcomes for specific regions and for a shorter duration than the entire testing period. This is a first of its study towards interpreting the forecasting model in drought studies, which could help understand the behaviour of drought variables.},\n\tlanguage = {en},\n\turldate = {2021-10-25},\n\tjournal = {Machine Learning with Applications},\n\tauthor = {Dikshit, Abhirup and Pradhan, Biswajeet},\n\tmonth = oct,\n\tyear = {2021},\n\tkeywords = {Deep learning, Drought forecasting, Explainable AI, Standard precipitation index},\n\tpages = {100192},\n}\n\n","author_short":["Dikshit, A.","Pradhan, B."],"key":"dikshit_explainable_2021","id":"dikshit_explainable_2021","bibbaseid":"dikshit-pradhan-explainableaiindroughtforecasting-2021","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S2666827021000967"},"keyword":["Deep learning","Drought forecasting","Explainable AI","Standard precipitation index"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["XJ7Gu6aiNbAiJAjbw","XvjRDbrMBW2XJY3p9","3C6BKwtiX883bctx4","5THezwiL4FyF8mm4G","RktFJE9cDa98BRLZF","qpxPuYKLChgB7ox6D","PfM5iniYHEthCfQDH","SZvSgtLYdBsPSQ3NM","iwKepCrWBps7ojhDx"],"keywords":["deep learning","drought forecasting","explainable ai","standard precipitation index"],"search_terms":["explainable","drought","forecasting","dikshit","pradhan"],"title":"Explainable AI in drought forecasting","year":2021}