Asosiy kontentga oʻtish
Maqola

Architecture diverse TabNet ensemble for crop type classification using harmonized multisource soil data

Abror Shavkatovich BuriboevDepartment of AI, Gachon University, Seongnam, Republic of KoreaAkhatov AbrorDepartment of AI, Samarkand State University, Samarkand, UzbekistanMamatov NarzulloDepartment of AI, Tashkent Institute of Irrigation and Agricultural Mechanization Engineers, National Research University, Tashkent, UzbekistanFayzullo NazarovDepartment of AI, Samarkand State University, Samarkand, UzbekistanYuldoshev YusufTashkent State University of EconomicsShavkat BuriboevDepartment of CE, Samarkand State Technical University, Samarkand, UzbekistanBazarbaev MurataliDepartment of Biomedical Engineering, Informatics and Biophysics, Tashkent State Medical University, Tashkent, UzbekistanAbbos AbduvaytovDepartment of IT, Samarkand Institute of Economics and Service, Samarkand, UzbekistanGayrat AchilovDepartment of Energy and Applied Sciences, Kimyo International University in Tashkent, Samarkand, UzbekistanJurabek KuvandikovDepartment of Computer Sciences and Programming, Djizakh Branch of National University of Uzbekistan, Jizzakh, UzbekistanRavshan IndiaminovDepartment of AI, Samarkand State University, Samarkand, UzbekistanHeung Seok JeonDepartment of Computer Engineering, Konkuk University, Chungju, Republic of KoreaCheolwon LeeDepartment of Computer Engineering, Konkuk University, Chungju, Republic of Korea
2026en
ABI

Annotatsiya

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.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba