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

2026-05-19

AI Summary

This work addresses three major challenges in environmental science—flood prediction, global weather forecasting, and domain-specific question answering—where conventional approaches suffer from high computational costs, inadequate uncertainty quantification, or limited interpretability. To this end, we propose an efficient, accurate, and interpretable deep learning framework for environmental intelligence: WaLeF and FIDLAr enable explainable coastal flood prediction and control; CoDiCast pioneers the use of conditional diffusion models for weather forecasting, explicitly quantifying predictive uncertainty; and Hypercube-RAG leverages structured text cubes to achieve accurate, efficient, and traceably explainable responses in environmental question answering. Experiments demonstrate that FIDLAr significantly outperforms baselines in Florida flood systems, CoDiCast delivers efficient probabilistic forecasts, and Hypercube-RAG effectively mitigates hallucination while enhancing reliability.

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.

Problem

• flood prediction
• weather forecasting
• scientific question-answering
• environmental intelligence
• large language models

Innovation

• Explainable AI
• Conditional Diffusion Model
• Retrieval-Augmented Generation
• Environmental Intelligence
• Uncertainty Quantification