Automated Landfill Detection Using Deep Learning: A Comparative Study of Lightweight and Custom Architectures with the AerialWaste Dataset

2025-08-23

AI Summary

To address the low efficiency, incomplete coverage, and high false-negative rate of manual inspections for illegal landfills, this paper proposes an automated detection method based on ensemble lightweight deep learning models and multi-level feature fusion. On the AerialWaste dataset (10,434 aerial images), we systematically evaluate MobileNetV2, GoogLeNet, DenseNet, and MobileViT, and design a model-ensemble framework to mitigate overfitting and enhance generalization. The proposed approach achieves robust binary classification on large-scale, heterogeneous aerial imagery, attaining 92.33% accuracy, 92.67% precision, 92.33% sensitivity, 92.41% F1-score, and 92.71% specificity—significantly outperforming individual baseline models. This work delivers an efficient, deployable, and intelligent solution for environmental remote sensing monitoring and regulatory enforcement.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Illegal landfills are posing as a hazardous threat to people all over the world. Due to the arduous nature of manually identifying the location of landfill, many landfills go unnoticed by authorities and later cause dangerous harm to people and environment. Deep learning can play a significant role in identifying these landfills while saving valuable time, manpower and resources. Despite being a burning concern, good quality publicly released datasets for illegal landfill detection are hard to find due to security concerns. However, AerialWaste Dataset is a large collection of 10434 images of Lombardy region of Italy. The images are of varying qualities, collected from three different sources: AGEA Orthophotos, WorldView-3, and Google Earth. The dataset contains professionally curated, diverse and high-quality images which makes it particularly suitable for scalable and impactful research. As we trained several models to compare results, we found complex and heavy models to be prone to overfitting and memorizing training data instead of learning patterns. Therefore, we chose lightweight simpler models which could leverage general features from the dataset. In this study, Mobilenetv2, Googlenet, Densenet, MobileVit and other lightweight deep learning models were used to train and validate the dataset as they achieved significant success with less overfitting. As we saw substantial improvement in the performance using some of these models, we combined the best performing models and came up with an ensemble model. With the help of ensemble and fusion technique, binary classification could be performed on this dataset with 92.33% accuracy, 92.67% precision, 92.33% sensitivity, 92.41% F1 score and 92.71% specificity.

Problem

• Detecting illegal landfills automatically using deep learning models
• Addressing overfitting in complex models through lightweight architectures
• Creating accurate landfill detection with aerial imagery classification

Innovation

• Used lightweight deep learning models
• Applied ensemble and fusion techniques
• Achieved high accuracy binary classification