Long-term drought prediction using deep neural networks based on geospatial weather data

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Marusov, Alexander, Grabar, Vsevolod, Maximov, Yury, Sotiriadi, Nazar, Bulkin, Alexander, Zaytsev, Alexey
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910524534423552
author Marusov, Alexander
Grabar, Vsevolod
Maximov, Yury
Sotiriadi, Nazar
Bulkin, Alexander
Zaytsev, Alexey
author_facet Marusov, Alexander
Grabar, Vsevolod
Maximov, Yury
Sotiriadi, Nazar
Bulkin, Alexander
Zaytsev, Alexey
contents The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting.
format Preprint
id arxiv_https___arxiv_org_abs_2309_06212
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Long-term drought prediction using deep neural networks based on geospatial weather data
Marusov, Alexander
Grabar, Vsevolod
Maximov, Yury
Sotiriadi, Nazar
Bulkin, Alexander
Zaytsev, Alexey
Machine Learning
The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting.
title Long-term drought prediction using deep neural networks based on geospatial weather data
topic Machine Learning
url https://arxiv.org/abs/2309.06212