Attention-based convolutional capsules for evapotranspiration estimation at scale. (June 2022)

• Record Type: Journal Article
• Authors: Armstrong, Samuel; Khandelwal, Paahuni; Padalia, Dhruv; Senay, Gabriel; Schulte, Darin; Andales, Allan; Breidt, F. Jay; Pallickara, Shrideep; Pallickara, Sangmi Lee
• Is Part Of: Environmental modelling & software. Volume 152(2022)
• Publication Date: 2022-06
• Subjects: Evapotranspiration -- Satellite imagery -- Neural networks -- Capsule networks -- Residual learning -- Attention-based learning; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2022.105366
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Evapotranspiration (ET) measures the amount of water lost from the Earth's surface to the atmosphere and is an integral metric for both agricultural and environmental sciences. Understanding and quantifying ET is critical for achieving effective management of freshwater and irrigation systems. However, current ET estimation models suffer from a trade-off between accuracy and spatial coverage. In this study, we introduce our model Quench, a neural network architecture that achieves highly-accurate ET estimates over large continuous spatial extents. Quench uses our novel Attention-Based Convolutional Capsule for its neural network layers to identify areas of focus and efficiently extract ET information from satellite imagery. Benchmarks that profile our model's performance show substantive improvements in accuracy, with up to 128% increase in accuracy compared to traditional convolutional-based and process-based models. Quench also demonstrates consistent model performance over high geospatial variability and a diverse array of regions, seasons, climates, and vegetations. Highlights: Evapotranspiration is the rate of water lost from the land to the atmosphere. Evapotranspiration models have a trade off between accuracy and spatial coverage. Using neural networks we created a high-accuracy, high-spatial coverage model, Quench. Quench uses our novel neural network layer the attention-based convolutional capsule. Quench provides state-of-the-art accuracy over a wide range of geospatial conditions.