Advancing Soil Organic Carbon Prediction: A Comprehensive Review of Technologies, AI, Process-Based and Hybrid...

Area of Science:

• Soil Science
• Environmental Science
• Agricultural Science

Background:

• Soil organic carbon (SOC) is crucial for climate change mitigation and sustainable agriculture.
• Accurate measurement, monitoring, and prediction of SOC are essential for these efforts.

Purpose of the Study:

• To review recent advancements in methodologies and technologies for SOC quantification.
• To highlight the integration of various techniques for improved SOC prediction.

Main Methods:

• Remote sensing (RS)
• Proximal soil sensing (PSS)
• Artificial intelligence (AI) including machine learning (ML) and deep learning (DL)
• Biogeochemical modelling
• Data fusion

Main Results:

• Integrating RS and PSS data with AI models improves SOC prediction accuracy.
• Deep learning (DL) often outperforms classical machine learning (ML).
• Incorporating biogeochemical model outputs enhances AI model accuracy and causal understanding.

Conclusions:

• Enhanced SOC prediction relies on integrating sensing technologies and AI (especially DL).
• Addressing limitations in biogeochemical models and expanding data availability are critical.
• Improving microbial influence representation and fostering interdisciplinary collaboration are key for future advancements.