Multi-Year Geospatial Reasoning using Interannually-Consistent Historical Predictions as a Free Input Modality

• URL: http://arxiv.org/abs/2608.05979v2
• Date: Mon, 10 Aug 2026 08:44:49 GMT
• Title: Multi-Year Geospatial Reasoning using Interannually-Consistent Historical Predictions as a Free Input Modality
• Abstract summary: We show that adding the prediction history raises crop-only F1 by 1.6 percentage points (pp) and, more importantly, corrects a recall-skewed error profile.<n>The approach is a low-cost recipe for any recurring geospatial or foundation model that emits class maps.
• Score: 0.07249400282852116
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning, and deep networks in particular, are increasingly used to derive higher-level Earth observation (EO) products such as annual land-cover and crop-type maps. Many are generated operationally: each year a new acquisition is processed, typically with the same model, extending a multi-year archive. In the process these systems accumulate two kinds of useful signal that are almost never fed back into the model: the system's own archive of past predictions, and ancillary layers produced by other partners in a processing consortium. Both are normally used outside the network, as rule-based post-processing or a fixed input mask. Using the Copernicus Land Monitoring Service High Resolution Layer (HRL) Croplands crop-type product as a testbed, we show that bringing both signals inside the model turns a single-year, single-task pixel classifier into one that reasons across years. We introduce a Crop Type (CTY) embedding encoder that represents each past prediction as a confidence-scaled, time-ordered categorical token and attends over the year axis, and we study how the externally provided Base Vegetation Layer (BVL) mask should be represented in the model's inputs and outputs. To compare designs fairly when they relabel non-crop pixels, we evaluate on the 18 crop classes only and report precision and recall separately. On a pan-European dataset of about 5.4M labelled pixels, adding the prediction history raises crop-only F1 by 1.6 percentage points (pp) and, more importantly, corrects a recall-skewed error profile, with the largest gains on perennial and tree crops (olives +4.6, fruits +3.7, nuts +3.2 pp). Representing the BVL mask consistently in both the history and the target year adds about 2.5 pp on the crop classes. The approach is a low-cost recipe for any recurring geospatial or foundation model that emits class maps.

Related papers

• Intercomparison of Machine Learning Algorithms for Remote Sensing-based In-season Crop Mapping [2.890903045620196]
  USDA Cropland Data Layer provides crop type labels at 30m resolution.<n>No product exists that maps crop types before harvest with satisfactory accuracy.<n>In-season crop type mapping is critical for food security in the face of increasingly extreme climate-related threats to crops.
  arXiv  Detail & Related papers  (2026-06-04T05:47:44Z)
• A Modelling and Evaluation Framework for EuroCrops-Driven Sentinel-2 Crop Segmentation [78.66324246922831]
  This work presents a pipeline for generating semantic-segmentation-ready agricultural datasets from Sentinel-2 imagery and EuroCrops parcel-level annotations.<n>The dataset contains 67,337 patches from five European countries and uses a reduced taxonomy of ten crop classes plus background.<n>A four-level U-Net with Group Normalization was trained using 10 Sentinel-2 spectral bands and a composite loss combining class-weighted cross-entropy and Dice loss.
  arXiv  Detail & Related papers  (2026-05-30T11:20:29Z)
• VFMF: World Modeling by Forecasting Vision Foundation Model Features [67.09340259579761]
  We introduce a generative forecaster that performs autoregressive flow matching in vision foundation models feature space.<n>We show that this latent information more effectively than previously used PCA-based alternatives, both for forecasting and other applications.<n>With matched architecture and compute, our method produces sharper and more accurate predictions than regression across all modalities.
  arXiv  Detail & Related papers  (2025-12-12T02:10:05Z)
• Bayesian Modelling of Multi-Year Crop Type Classification Using Deep Neural Networks and Hidden Markov Models [12.282079123411947]
  temporal consistency of yearly land-cover maps is of great importance to model the evolution and change of the land cover over the years.<n>In this paper, we focus the attention on a novel approach to classification of yearly satellite image time series (SITS) that combines deep learning with Bayesian modelling.<n>The proposed approach aims to capture both i) intricate temporal correlations in yearly SITS and ii) specific patterns in multiyear crop type sequences.
  arXiv  Detail & Related papers  (2025-10-08T13:33:32Z)
• Uncertainty-aware Bayesian machine learning modelling of land cover classification [0.0]
  We propose a Bayesian classification framework using generative modelling to take account of input measurement uncertainty.<n>We benchmark the performance of the model against more popular classification models used in land cover maps such as random forests and neural networks.
  arXiv  Detail & Related papers  (2025-03-27T13:59:19Z)
• Localized Randomized Smoothing for Collective Robustness Certification [60.83383487495282]
  We propose a more general collective robustness certificate for all types of models. We show that this approach is beneficial for the larger class of softly local models. The certificate is based on our novel localized randomized smoothing approach.
  arXiv  Detail & Related papers  (2022-10-28T14:10:24Z)
• A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning [0.716879432974126]
  Sen4AgriNet is a Sentinel-2 based time series multi country benchmark dataset for agricultural monitoring applications. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. It contains 42.5 million parcels, which makes it significantly larger than other available archives.
  arXiv  Detail & Related papers  (2022-04-02T23:14:46Z)
• Transformers Can Do Bayesian Inference [56.99390658880008]
  We present Prior-Data Fitted Networks (PFNs) PFNs leverage in-context learning in large-scale machine learning techniques to approximate a large set of posteriors. We demonstrate that PFNs can near-perfectly mimic Gaussian processes and also enable efficient Bayesian inference for intractable problems.
  arXiv  Detail & Related papers  (2021-12-20T13:07:39Z)
• Two-dimensional Deep Regression for Early Yield Prediction of Winter Wheat [0.0]
  We tackle the yield prediction problem using a Convolutional Neural Network (CNN) trained on data that combines radar satellite imagery and on-ground information. We utilize radar data acquired from the Sentinel-1 satellites, while the on-ground data correspond to a set of six features. We show that our proposed methodology yields better results than five compared methods.
  arXiv  Detail & Related papers  (2021-11-15T20:40:15Z)
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation [97.61605021985062]
  We propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented annotations of different datasets. This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets. In order to better model the relationship among images and classes from different datasets, we extend the pixel level embeddings via cross dataset mixing.
  arXiv  Detail & Related papers  (2021-06-08T06:13:11Z)
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching [58.720142291102135]
  This research project focuses on the use of autoencoders networks to construct a continuous parameterization for facies models. We benchmark seven different formulations, including VAE, generative adversarial network (GAN), Wasserstein GAN, variational auto-encoding GAN, principal component analysis (PCA) with cycle GAN, PCA with transfer style network and VAE with style loss.
  arXiv  Detail & Related papers  (2020-05-08T21:32:42Z)

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.