Attention-Based Ensemble Learning for Crop Classification Using Landsat 8-9 Fusion

2025-06-23

AI Summary

Low classification accuracy in the Central Punjab irrigation zone arises from multi-crop intercropping and temporal spectral confusion in satellite imagery. Method: We constructed a high-quality remote sensing dataset integrating Landsat 8/9 images, comprising 50,835 labeled samples, with preprocessing including radiometric calibration, atmospheric correction, and image fusion; we further incorporated multidimensional spectral and vegetation indices (e.g., NDVI, SAVI, RECI, NDRE). An attention-enhanced ensemble learning framework was innovatively designed to dynamically weight critical bands and indices, improving discriminability among crop classes in complex agricultural landscapes. Results: The proposed method significantly outperforms conventional random forest and CNN baselines, achieving an overall classification accuracy of 92.7% for major crops. This validates the effectiveness and scalability of the “remote sensing data optimization + interpretable feature-weighted modeling” paradigm for large-scale irrigated agriculture monitoring.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Remote sensing offers a highly effective method for obtaining accurate information on total cropped area and crop types. The study focuses on crop cover identification for irrigated regions of Central Punjab. Data collection was executed in two stages: the first involved identifying and geocoding six target crops through field surveys conducted in January and February 2023. The second stage involved acquiring Landsat 8-9 imagery for each geocoded field to construct a labelled dataset. The satellite imagery underwent extensive pre-processing, including radiometric calibration for reflectance values, atmospheric correction, and georeferencing verification to ensure consistency within a common coordinate system. Subsequently, image fusion techniques were applied to combine Landsat 8 and 9 spectral bands, creating a composite image with enhanced spectral information, followed by contrast enhancement. During data acquisition, farmers were interviewed, and fields were meticulously mapped using GPS instruments, resulting in a comprehensive dataset of 50,835 data points. This dataset facilitated the extraction of vegetation indices such as NDVI, SAVO, RECI, and NDRE. These indices and raw reflectance values were utilized for classification modeling using conventional classifiers, ensemble learning, and artificial neural networks. A feature selection approach was also incorporated to identify the optimal feature set for classification learning. This study demonstrates the effectiveness of combining remote sensing data and advanced modeling techniques to improve crop classification accuracy in irrigated agricultural regions.

Problem

• Improving crop classification accuracy using Landsat 8-9 fusion data
• Identifying crop types in irrigated regions of Central Punjab
• Combining remote sensing and machine learning for enhanced classification

Innovation

• Attention-based ensemble learning for classification
• Landsat 8-9 fusion with enhanced spectral data
• Multi-feature extraction with vegetation indices