aiqbench analysis
This paper benchmarks Tabular Deep Learning models against classical tree ensembles for urban land cover classification, demonstrating that TDL architectures can match or exceed traditional baselines when handling non-linear feature interactions and class imbalance effectively. The study provides a reproducible pipeline using tabular data derived from aerial imagery, offering practical insights for remote sensing applications where deep learning may complement established machine learning workflows.
Tabular Deep Learning vs Classical Machine Learning for Urban Land Cover Classification
arXiv:2609.19010v1 Announce Type: cross Abstract: Urban Land Cover (ULC) classification plays a crucial role in urban planning, environmental monitoring, and sustainable development. We study this task using the ULC dataset from the UCI Machine Learning Repository, which includes tabular features derived from high-resolution aerial imagery across nine classes (e.g., roads, trees, grass, water). The dataset presents typical remote sensing challenges, including high dimensionality, heterogeneous features, and class imbalance. In a unified, reproducible pipeline, we benchmark classical machine learning models (e.g., Logistic Regression, SVM, Random Forest, XGBoost, CatBoost) against Tabular Deep Learning (TDL) models (TabNet, FT-Transformer, TabTransformer, TabSeq, and 1D CNNs). To address class imbalance, we employ weighted cross-entropy loss for TDL models and evaluate performance using accuracy, macro-precision, macro-recall, macro-F1, AUC-ROC, and confusion matrices. Our results show that while tree ensembles remain strong general baselines, TDL models can match or exceed their performance when non-linear interactions are significant and imbalance handling is effective, providing complementary advantages for urban land cover mapping. See code: https://github.com/mtesha/tdl-vs-ml-urbanlandcover
Abstract:Urban Land Cover (ULC) classification plays a crucial role in urban planning, environmental monitoring, and sustainable development. We study this task using the ULC dataset from the UCI Machine Learning Repository, which includes tabular features derived from high-resolution aerial imagery across nine classes (e.g., roads, trees, grass, water). The dataset presents typical remote sensing challenges, including high dimensionality, heterogeneous features, and class imbalance. In a unified, reproducible pipeline, we benchmark classical machine learning models (e.g., Logistic Regression, SVM, Random Forest, XGBoost, CatBoost) against Tabular Deep Learning (TDL) models (TabNet, FT-Transformer, TabTransformer, TabSeq, and 1D CNNs). To address class imbalance, we employ weighted cross-entropy loss for TDL models and evaluate performance using accuracy, macro-precision, macro-recall, macro-F1, AUC-ROC, and confusion matrices. Our results show that while tree ensembles remain strong general baselines, TDL models can match or exceed their performance when non-linear interactions are significant and imbalance handling is effective, providing complementary advantages for urban land cover mapping. See code: this https URL
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2609.19010 [cs.LG]
(or arXiv:2609.19010v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.19010 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
Multi-Modal Spatio-Temporal Graph Neural Network with Mixture of Experts for Soil Organic Carbon Prediction
arXiv · Jun 16, 2026
When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobe
arXiv · Jul 28, 2026
Bring your own model with Amazon SageMaker AI: Script mode in SDK v3
AWS · Aug 26, 2026
News Archive 2026
Quantum Computing Report · Jul 25, 2026