ConvLSTM-based drought prediction using vegetation health index (VHI)

Soo-Jin Lee; Yangwon Lee

doi:10.1117/12.2679972

17 October 2023 ConvLSTM-based drought prediction using vegetation health index (VHI)

Soo-Jin Lee, Yangwon Lee

Proceedings Volume 12727, Remote Sensing for Agriculture, Ecosystems, and Hydrology XXV; 1272703 (2023) https://doi.org/10.1117/12.2679972
Event: SPIE Remote Sensing, 2023, Amsterdam, Netherlands

Abstract

The temperature rise due to climate change is expected to increase the frequency of droughts. These droughts not only pose a significant threat to agriculture and food security, but also increase the risk of additional disasters such as wildfires. Therefore, accurate drought monitoring and prediction are crucial. Predicted drought information can help strengthen policies related to agriculture and water management and prepare for drought response. Generally, the surface drought condition is monitored through satellite-based drought indices. Among various drought indices, the vegetation health index (VHI) which comprehensively combines temperature and vegetation status, is mainly used. In this study, we propose a model for predicting VHI time series data using Convolutional Long Short-Term Memory (ConvLSTM). ConvLSTM is a model that combines Convolutional Neural Network (CNN) and LSTM and can learn both temporal and spatial characteristics of time series data while preserving its spatial features. Therefore, it is being used in various fields such as image and video processing, and weather forecasting, where local features need to be considered. The study area is South Korea, and long-term weekly VHI data provided by NOAA were used for short-term prediction. The proposed model can be useful for drought prediction considering local features.

Conference Presentation

Citation Download Citation

Soo-Jin Lee and Yangwon Lee "ConvLSTM-based drought prediction using vegetation health index (VHI)", Proc. SPIE 12727, Remote Sensing for Agriculture, Ecosystems, and Hydrology XXV, 1272703 (17 October 2023); https://doi.org/10.1117/12.2679972

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available