Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage

• URL: http://arxiv.org/abs/2510.10799v1
• Date: Sun, 12 Oct 2025 20:34:45 GMT
• Title: Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage
• Authors: Wanshu Nie, Sujay V. Kumar, Junyu Chen, Long Zhao, Olya Skulovich, Jinwoong Yoo, Justin Pflug, Shahryar Khalique Ahmad, Goutam Konapala,
• Abstract summary: We show that linear regression is a robust benchmark, outperforming the more complex LSTM and Temporal Fusion Transformer for terrestrial water storage prediction.<n>Our findings highlight the importance of including traditional statistical models as benchmarks when developing and evaluating deep learning models.<n>We emphasize the critical need to establish globally representative benchmark datasets that capture the combined impact of natural variability and human interventions.
• Score: 11.462378606382439
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in machine learning such as Long Short-Term Memory (LSTM) models and Transformers have been widely adopted in hydrological applications, demonstrating impressive performance amongst deep learning models and outperforming physical models in various tasks. However, their superiority in predicting land surface states such as terrestrial water storage (TWS) that are dominated by many factors such as natural variability and human driven modifications remains unclear. Here, using the open-access, globally representative HydroGlobe dataset - comprising a baseline version derived solely from a land surface model simulation and an advanced version incorporating multi-source remote sensing data assimilation - we show that linear regression is a robust benchmark, outperforming the more complex LSTM and Temporal Fusion Transformer for TWS prediction. Our findings highlight the importance of including traditional statistical models as benchmarks when developing and evaluating deep learning models. Additionally, we emphasize the critical need to establish globally representative benchmark datasets that capture the combined impact of natural variability and human interventions.

Related papers

• Extreme value forecasting using relevance-based data augmentation with deep learning models [3.503370263836711]
  In this study, we present a data augmentation framework for extreme value forecasting.<n>We use deep learning models in combination with data augmentation models such as GANs and synthetic minority oversampling technique (SMOTE)<n>Our results indicate that the SMOTE-based strategy consistently demonstrated superior adaptability, leading to improved performance across both short and long-horizon forecasts.
  arXiv  Detail & Related papers  (2025-10-02T06:10:27Z)
• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning [77.120955854093]
  We show that data diversity can be a strong predictor of generalization in language models.<n>We introduce G-Vendi, a metric that quantifies diversity via the entropy of model-induced gradients.<n>We present Prismatic Synthesis, a framework for generating diverse synthetic data.
  arXiv  Detail & Related papers  (2025-05-26T16:05:10Z)
• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO)<n>In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery.<n>We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy [104.48511402784763]
  Performance Law for SR models aims to theoretically investigate and model the relationship between model performance and data quality.<n>We propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics.
  arXiv  Detail & Related papers  (2024-11-30T10:56:30Z)
• Approaches for enhancing extrapolability in process-based and data-driven models in hydrology [0.16735447464058464]
  This paper reviews and compares methods for assessing and enhancing the extrapolability of process-based and data-driven hydrological models. Key strategies include the use of leave-one-out cross-validation and similarity-based methods to evaluate model performance in ungauged regions. Deep learning, transfer learning, and domain adaptation techniques are also promising in their potential to improve model predictions in data-sparse and extreme conditions.
  arXiv  Detail & Related papers  (2024-08-13T17:59:24Z)
• DeepVARMA: A Hybrid Deep Learning and VARMA Model for Chemical Industry Index Forecasting [14.738606795298043]
  This paper proposes a new prediction model: DeepVARMA, which combines LSTM and VARMAX models. The experimental results show that the new model achieves the best prediction accuracy. This study provides more accurate tools and methods for future development and scientific decision-making in the chemical industry.
  arXiv  Detail & Related papers  (2024-04-26T09:15:26Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Differentiable, learnable, regionalized process-based models with physical outputs can approach state-of-the-art hydrologic prediction accuracy [1.181206257787103]
  We show that differentiable, learnable, process-based models (called delta models here) can approach the performance level of LSTM for the intensively-observed variable (streamflow) with regionalized parameterization. We use a simple hydrologic model HBV as the backbone and use embedded neural networks, which can only be trained in a differentiable programming framework.
  arXiv  Detail & Related papers  (2022-03-28T15:06:53Z)
• Transfer learning to improve streamflow forecasts in data sparse regions [0.0]
  We study the methodology behind Transfer Learning (TL) through fine-tuning and parameter transferring for better generalization performance of streamflow prediction in data-sparse regions. We propose a standard recurrent neural network in the form of Long Short-Term Memory (LSTM) to fit on a sufficiently large source domain dataset. We present a methodology to implement transfer learning approaches for hydrologic applications by separating the spatial and temporal components of the model and training the model to generalize.
  arXiv  Detail & Related papers  (2021-12-06T14:52:53Z)
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [73.03458424369657]
  In real-time forecasting in public health, data collection is a non-trivial and demanding task. 'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
  arXiv  Detail & Related papers  (2021-06-08T14:48:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.