Architecture diverse TabNet ensemble for crop type classification using harmonized multisource soil data
Abstract
Accurate analysis of heterogeneous soil records can support data-driven agricultural planning, but integrating datasets from different laboratories and public repositories introduces challenges related to inconsistent units, source-dependent distributions, missing values, duplicate observations, and potential information leakage. This study proposes ADWTabNet, an architecture-diverse TabNet ensemble for multiclass crop-type classification using harmonized multi-source soil data. The integrated dataset contained 18,237 observations representing seven crop classes and a broad set of chemical, physical, microbiological, and categorical soil properties. The proposed framework combines unit standardization, duplicate control, source-distribution harmonization, separate categorical and numerical imputation, tree-structured Parzen estimator-based hyperparameter optimization, structurally diverse TabNet models, probability-level ensemble fusion, calibration assessment, and attention-based interpretation. Under the evaluated stratified holdout protocol, XGBoost achieved a test accuracy of 0.8724 and a macro F1-score of 0.8670. Baseline TabNet improved these values to 0.8863 and 0.8822, respectively, while the TPE-optimized TabNet reached an accuracy of 0.8951 and reduced log loss from 0.3325 to 0.2566. The proposed ADWTabNet ensemble obtained the best reported performance, with a test accuracy of 0.9053, macro F1-score of 0.9025, weighted F1-score of 0.9050, macro ROC–AUC of 0.9930, and normalized multiclass Brier score of 0.0193. Repeated-run evaluation confirmed a stable advantage over the optimized individual TabNet, whereas the difference between validation-weighted and equal architecture-diverse averaging was not statistically significant. Aggregated TabNet attention ranked humus, phosphorus, electrical conductivity, nitrogen, and pH among the leading predictors, and this ranking was independently supported by permutation-importance analysis. These findings demonstrate improved crop-type classification within the evaluated integrated multi-source dataset. However, external validation using previously unseen laboratories and geographic regions is required before broader transferability can be established.
Related
- Geospatial suitability of cacao in Amazonas (Peru): An ensemble predictive modeling approach (BIOMOD2) integrating multisource data, territorial management, and plant health
- SeverYX: An ensemble framework for robust variant severity classification
- Genetic Dissection of Pea Nodulated Root Architecture and Early Rhizobial Partner Choice Across a Diverse 335-Line Panel
- Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer's Disease Drug Discovery
- NANHA - Neurostimulation in Atypical Neurodevelopment: a Harmonized Atlas
BibTeX
@article{buriboev2026architecture,
title = {{Architecture diverse TabNet ensemble for crop type classification using harmonized multisource soil data}},
author = {Abror Shavkatovich Buriboev and Akhatov Abror and Mamatov Narzullo and Nazarov Fayzullo and Yuldoshev Yusuf and Shavkat Buriboyev and Muratali Bazarbaev and Abbos Abduvaytov and Gayrat Achilov and Jurabek Kuvandikov and Ravshan Indiaminov and Heung Seok Jeon and Cheolwon Lee},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75366-7},
url = {https://www.nature.com/articles/s41598-026-75366-7},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Architecture diverse TabNet ensemble for crop type classification using harmonized multisource soil data
AU - Abror Shavkatovich Buriboev
AU - Akhatov Abror
AU - Mamatov Narzullo
AU - Nazarov Fayzullo
AU - Yuldoshev Yusuf
AU - Shavkat Buriboyev
AU - Muratali Bazarbaev
AU - Abbos Abduvaytov
AU - Gayrat Achilov
AU - Jurabek Kuvandikov
AU - Ravshan Indiaminov
AU - Heung Seok Jeon
AU - Cheolwon Lee
PY - 2026
DA - 2026/10/18
JO - Scientific Reports
DO - 10.1038/s41598-026-75366-7
UR - https://www.nature.com/articles/s41598-026-75366-7
AB - Accurate analysis of heterogeneous soil records can support data-driven agricultural planning, but integrating datasets from different laboratories and public repositories introduces challenges related to inconsistent units, source-dependent distributions, missing values, duplicate observations, and potential information leakage. This study proposes ADWTabNet, an architecture-diverse TabNet ensemble for multiclass crop-type classification using harmonized multi-source soil data. The integrated dataset contained 18,237 observations representing seven crop classes and a broad set of chemical, physical, microbiological, and categorical soil properties. The proposed framework combines unit standardization, duplicate control, source-distribution harmonization, separate categorical and numerical imputation, tree-structured Parzen estimator-based hyperparameter optimization, structurally diverse TabNet models, probability-level ensemble fusion, calibration assessment, and attention-based interpretation. Under the evaluated stratified holdout protocol, XGBoost achieved a test accuracy of 0.8724 and a macro F1-score of 0.8670. Baseline TabNet improved these values to 0.8863 and 0.8822, respectively, while the TPE-optimized TabNet reached an accuracy of 0.8951 and reduced log loss from 0.3325 to 0.2566. The proposed ADWTabNet ensemble obtained the best reported performance, with a test accuracy of 0.9053, macro F1-score of 0.9025, weighted F1-score of 0.9050, macro ROC–AUC of 0.9930, and normalized multiclass Brier score of 0.0193. Repeated-run evaluation confirmed a stable advantage over the optimized individual TabNet, whereas the difference between validation-weighted and equal architecture-diverse averaging was not statistically significant. Aggregated TabNet attention ranked humus, phosphorus, electrical conductivity, nitrogen, and pH among the leading predictors, and this ranking was independently supported by permutation-importance analysis. These findings demonstrate improved crop-type classification within the evaluated integrated multi-source dataset. However, external validation using previously unseen laboratories and geographic regions is required before broader transferability can be established.
SN - 2045-2322
ER -