Early Crop Type Classification Based on Seasonal Spectral Features and Machine Learning Methods
Authors:
- Ainagul AlimagambetovaAAAinagul Alimagambetova
- Moldir YessenovaMYMoldir Yessenova
- Assem KonyrkhanovaAKAssem Konyrkhanova
- Ten TatyanaTTTen Tatyana
- Aliya BeissegulAliya Beissegul
- Zhuldyz TashenovaZTZhuldyz Tashenova
- Kuanysh KadirkulovKKKuanysh Kadirkulov
- Aitimova UlzadaAUAitimova Ulzada
- Gulalem MauinaGMGulalem Mauina
Open Access
- 10 April 2026
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 14 (4) , 221
Abstract
This paper explores the feasibility of early-season crop classification based on Sentinel-2-time series using the TimeSen2Crop dataset (≈1 million pixels, 16 crops). The aim of the study was to evaluate the spectral-phenological separability of crops during the season and compare the performance of classical tabular algorithms, deep sequence models, and a seasonally oriented hybrid stacking scheme. Based on multispectral observations, a feature set was formed from 9 optical channels and 13 vegetation indices for 30 dates. F-criteria were calculated, confirming a sharp increase in interclass separability during the active vegetative growth phase and substantiating three time series truncation scenarios (early, early + mid-season, and full season). Random Forest (macro-F1: 0.46/0.74/0.75) was used as the base tabular model. LSTM, BiLSTM, GRU, 1D-CNN, and Transformer were trained in parallel, with Transformer showing the best results among the deep architectures (0.42/0.68/0.78). The main contribution of the work is a hybrid multi-layer stacking scheme combining heterogeneous base algorithms and OOF meta-features, which provides the highest quality (0.51/0.83/0.86) in all scenarios. The obtained results confirm the effectiveness of phenology-oriented selection of time windows, informative indices, and hybrid ensemble learning for improving the accuracy of early-season crop monitoring.Keywords
Funding Information
- Science Committee of the Ministry of Education and Science of the Republic of Kazakhstan (AP25793889)
This publication has 26 references indexed in Scilit:
- A Hybrid Spatio-Temporal Model for Probabilistic Mapping of Soil Salinity in Arid RegionsIEEE Access, 2026
- Thirty-Year Analyses of Seasonal NDVI and Climatic Drivers Across Different Land Cover Types and Biogeographical Regions in EuropeIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025
- Assessing feature extraction, selection, and classification combinations for crop mapping using Sentinel-2 time series: A case study in northern ItalyRemote Sensing Applications: Society and Environment, 2025
- Improving cross-regional model transfer performance in crop classification by crop time series correctionGeo-spatial Information Science, 2024
- A source-free unsupervised domain adaptation method for cross-regional and cross-time crop mapping from satellite image time seriesRemote Sensing of Environment, 2024
- Understanding the potentials of early-season crop type mapping by using Landsat-8, Sentinel-1/2, and GF-1/6 dataComputers and Electronics in Agriculture, 2024
- Analyzing Disease and Pest Dynamics in Steppe Crop Using Structured DataIEEE Access, 2024
- Boosting crop classification by hierarchically fusing satellite, rotational, and contextual dataRemote Sensing of Environment, 2024
- Self-supervised pre-training for large-scale crop mapping using Sentinel-2 time seriesISPRS Journal of Photogrammetry and Remote Sensing, 2024
- A deep learning framework for crop mapping with reconstructed Sentinel-2 time series imagesComputers and Electronics in Agriculture, 2023