University of Florida Homepage

Machine Learning versus Deep Learning in Land System Science: A Decision-Making Framework for Effective Land Classification

Image of a satellite over the Earth. Text says "Frontiers in Remote Sensing."

SOUTHWORTH, SMITH, SAFAEI, RAHAMAN, ALRUZUQ, TEFERA – Machine Learning versus Deep Learning in Land System Science: A Decision-Making Framework for Effective Land Classification

Jane Southworth, Audrey C. Smith, Mohammad Safaei, Mashoukur Rahaman, Ali Alruzuq, Bewuket B. Tefera, Carly S. Muir, Hannah V. Herrero

Article first published online: 8 APRIL 2024

DOI: https://doi.org/10.3389/frsen.2024.1374862

ABSTRACT: This review explores the comparative utility of machine learning (ML) and deep learning (DL) in land system science (LSS) classification tasks. Through a comprehensive assessment, the study reveals that while DL techniques have emerged with transformative potential, their application in LSS often faces challenges related to data availability, computational demands, model interpretability, and overfitting. In many instances, traditional ML models currently present more effective solutions, as illustrated in our decision-making framework. Integrative opportunities for enhancing classification accuracy include data integration from diverse sources, the development of advanced DL architectures, leveraging unsupervised learning, and infusing domain-specific knowledge. The research also emphasizes the need for regular model evaluation, the creation of diversified training datasets, and fostering interdisciplinary collaborations. Furthermore, while the promise of DL for future advancements in LSS is undeniable, present considerations often tip the balance in favor of ML models for many classification schemes. This review serves as a guide for researchers, emphasizing the importance of choosing the right computational tools in the evolving landscape of LSS, to achieve reliable and nuanced land-use change data.

Read the full publication in Frontiers in Remote Sensing.