Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems

TL;DR

This paper presents innovative AI-based methods for environmental science, including deep learning models for flood prediction, a diffusion model for weather forecasting, and a structured retrieval system for environmental question-answering, all emphasizing accuracy, efficiency, and explainability.

Contribution

The paper introduces novel AI approaches tailored to environmental challenges, improving prediction accuracy, computational efficiency, and interpretability over existing methods.

Findings

FIDLAr outperforms baselines in flood management accuracy and efficiency.

CoDiCast achieves accurate probabilistic weather forecasts with uncertainty quantification.

Hypercube-RAG effectively balances accuracy, efficiency, and explainability in environmental QA.

Abstract

Environmental science plays a pivotal role in safeguarding ecosystems, a domain driven by large-scale, heterogeneous data. In the big data era, artificial intelligence (AI) has emerged as a transformative tool for learning patterns and supporting decision-making. This dissertation develops AI-based approaches tailored to complex environmental science problems to achieve Environmental Intelligence, studying three specific challenges. First, we focus on flood prediction and management in coastal river systems. Conventional physics-based models are computationally intensive, limiting real-time application. To overcome this, we propose a deep learning (DL)-based model, WaLeF, for water level forecasting, and a forecast-informed DL model, FIDLAr, to manage water levels. Evaluated in a flood-prone coastal system in South Florida characterized by extreme rainfall and sea level fluctuations, FIDLAr outperforms baselines in accuracy and efficiency while providing interpretable outputs. Second, we target global weather prediction, which is challenged by massive data scale. Traditional physics methods are deterministic and computationally heavy. We propose CoDiCast, a conditional diffusion model tailored for probabilistic weather forecasting. Adapted from generative AI for predictive tasks, experiments show CoDiCast achieves accurate, efficient forecasts with explicit uncertainty quantification. Lastly, we address scientific question-answering in environmental science. When answering in-domain questions, large language models (LLMs) often suffer from hallucinations due to out-of-date or limited knowledge. While retrieval-augmented generation (RAG) retrieves domain-specific knowledge, existing methods trade off accuracy, efficiency, or explainability. We propose Hypercube-RAG, built on a structured text cube framework, which successfully exhibits all three properties simultaneously.