Data-Centric AI for Tropical Agricultural Mapping: Challenges, Strategies and Scalable Solutions

2025-10-17

AI Summary

Tropical agricultural remote sensing mapping faces critical challenges including scarcity of high-quality labeled data, frequent cloud cover, high crop diversity, and poor cross-regional generalization. Method: To address these, we propose a Data-Centric Artificial Intelligence (DCAI) framework that shifts from the conventional model-centric paradigm. Our approach systematically integrates nine established techniques—including confidence learning, core-set selection, active learning, and multi-strategy data augmentation—into an end-to-end, high-fidelity data curation pipeline. Contribution/Results: Evaluated across 25 distinct strategy configurations, the resulting pipeline is scalable and deployment-ready. Experiments demonstrate substantial improvements in model robustness and cross-regional generalization, achieving consistent performance gains across diverse crops and geographic regions. The framework effectively mitigates data scarcity and domain shift, enabling reliable large-scale tropical agricultural mapping.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Security and Privacy: Data transparency and provenance

Abstract

Mapping agriculture in tropical areas through remote sensing presents unique challenges, including the lack of high-quality annotated data, the elevated costs of labeling, data variability, and regional generalisation. This paper advocates a Data-Centric Artificial Intelligence (DCAI) perspective and pipeline, emphasizing data quality and curation as key drivers for model robustness and scalability. It reviews and prioritizes techniques such as confident learning, core-set selection, data augmentation, and active learning. The paper highlights the readiness and suitability of 25 distinct strategies in large-scale agricultural mapping pipelines. The tropical context is of high interest, since high cloudiness, diverse crop calendars, and limited datasets limit traditional model-centric approaches. This tutorial outlines practical solutions as a data-centric approach for curating and training AI models better suited to the dynamic realities of tropical agriculture. Finally, we propose a practical pipeline using the 9 most mature and straightforward methods that can be applied to a large-scale tropical agricultural mapping project.

Problem

• Mapping tropical agriculture faces data scarcity and quality issues
• Addressing cloud cover and crop diversity challenges in remote sensing
• Developing scalable data-centric AI solutions for agricultural mapping

Innovation

• Data-Centric AI pipeline prioritizing data quality
• Confident learning and core-set selection techniques
• Practical pipeline with nine mature scalable methods