# Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework

arXiv: https://arxiv.org/abs/2509.14563 · HTML: https://mlsanity.com/paper/2509.14563/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [TSMixer: An All-MLP Architecture for Time Series Forecasting](https://mlsanity.com/paper/2303.06053/) (2023)
- [Neural General Circulation Models for Weather and Climate](https://mlsanity.com/paper/2311.07222/) (2023)
- [Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data](https://mlsanity.com/paper/1612.08544/) (2016)
- [Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems](https://mlsanity.com/paper/2003.04919/) (2020)
- [Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets](https://mlsanity.com/paper/1907.08456/) (2019)
- [A trans-disciplinary review of deep learning research for water resources scientists](https://mlsanity.com/paper/1712.02162/) (2017)
- [Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.08826/) (2025)
- [Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning](https://mlsanity.com/paper/2011.05369/) (2020)
- [Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science](https://mlsanity.com/paper/2502.06084/) (2025)
- [Adaptive Process-Guided Learning: An Application in Predicting Lake DO Concentrations](https://mlsanity.com/paper/2411.12973/) (2024)
- [Combining Satellite and Weather Data for Crop Type Mapping: An Inverse Modelling Approach](https://mlsanity.com/paper/2401.15875/) (2024)
- [A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations](https://mlsanity.com/paper/2410.11247/) (2024)
- [RAG for Geoscience: What We Expect, Gaps and Opportunities](https://mlsanity.com/paper/2508.11246/) (2025)
- [Foundation Models for Environmental Science: A Survey of Emerging Frontiers](https://mlsanity.com/paper/2504.04280/) (2025)
- [A Survey of Foundation Models for Environmental Science](https://mlsanity.com/paper/2503.03142/) (2025)

## Built on by (most cited first, 2 of 2)

- [Retrieval-Augmented Multi-scale Framework for County-Level Crop Yield Prediction Across Large Regions](https://mlsanity.com/paper/2603.07305/) (2026)
- [PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling](https://mlsanity.com/paper/2607.20230/) (2026)

## Abstract (arXiv)

The discovery of environmental knowledge depends on labeled task-specific data, but is often constrained by the high cost of data collection. Existing machine learning approaches usually struggle to generalize in data-sparse or atypical conditions. To this end, we propose an Augmentation-Adaptive Self-Supervised Learning (A2SL) framework, which retrieves relevant observational samples to enhance modeling of the target ecosystem. Specifically, we introduce a multi-level pairwise learning loss to train a scenario encoder that captures varying degrees of similarity among scenarios. These learned similarities drive a retrieval mechanism that supplements a target scenario with relevant data from different locations or time periods. Furthermore, to better handle variable scenarios, particularly under atypical or extreme conditions where traditional models struggle, we design an augmentation-adaptive mechanism that selectively enhances these scenarios through targeted data augmentation. Using freshwater ecosystems as a case study, we evaluate A2SL in modeling water temperature and dissolved oxygen dynamics in real-world lakes. Experimental results show that A2SL significantly improves predictive accuracy and enhances robustness in data-scarce and atypical scenarios. Although this study focuses on freshwater ecosystems, the A2SL framework offers a broadly applicable solution in various scientific domains.