Attention-based Convolutional Capsules for Evapotranspiration Estimation at Scale
Armstrong S, Khandelwal P, Padalia D, Senay G, Schulte D, Andales A, Breidt FJ, Pallickara S, Pallickara SL. 2022. Attention-based Convolutional Capsules for Evapotranspiration Estimation at Scale. Environmental Modelling and Software. 152:1-13
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.
- Type
- Journal Article
- Authors
- Armstrong, Samuel; Khandelwal, Paahuni; Padalia, Dhruv; Senay, Gabriel; Schulte, Darin; Andales, Allan; Breidt, F; Pallickara, Shrideep; Pallickara, Sangmi
- Units
- GRSM , ROMO
- Keywords
- Attention-based learning, Capsule networks, Evapotranspiration, GRSM-01211, National Ecological Observatory Network, NEON, Neural networks, Residual learning, Satellite imagery