Knowledge Guided Encoder-Decoder Framework: Integrating Multiple Physical Models for Agricultural Ecosystem Modeling

TL;DR

This paper introduces a knowledge-guided encoder-decoder framework that integrates multiple physical models and language processing to improve agricultural ecosystem predictions across diverse scenarios.

Contribution

It presents a novel model that combines physical models with language understanding to enhance generalizability and robustness in ecological variable prediction.

Findings

Effective in predicting carbon and nitrogen fluxes across multiple sites.

Robust under various data distribution shifts.

Outperforms traditional models in accuracy and adaptability.

Abstract

Agricultural monitoring is critical for ensuring food security, maintaining sustainable farming practices, informing policies on mitigating food shortage, and managing greenhouse gas emissions. Traditional process-based physical models are often designed and implemented for specific situations, and their parameters could also be highly uncertain. In contrast, data-driven models often use black-box structures and does not explicitly model the inter-dependence between different ecological variables. As a result, they require extensive training data and lack generalizability to different tasks with data distribution shifts and inconsistent observed variables. To address the need for more universal models, we propose a knowledge-guided encoder-decoder model, which can predict key crop variables by leveraging knowledge of underlying processes from multiple physical models. The proposed method also integrates a language model to process complex and inconsistent inputs and also utilizes it to implement a model selection mechanism for selectively combining the knowledge from different physical models. Our evaluations on predicting carbon and nitrogen fluxes for multiple sites demonstrate the effectiveness and robustness of the proposed model under various scenarios.