SSL-SoilNet: A Hybrid Transformer-based Framework with Self-Supervised Learning for Large-scale Soil Organic Carbon Prediction

TL;DR

This paper introduces SSL-SoilNet, a hybrid transformer-based self-supervised learning framework that significantly improves large-scale soil organic carbon prediction accuracy using multimodal data and pretrained models.

Contribution

It presents a novel self-supervised contrastive learning approach with pretrained Vision Transformers and Transformers for climate data, enhancing soil carbon mapping accuracy over traditional methods.

Findings

Outperforms traditional supervised models like random forest and gradient boosting.

Achieves higher accuracy metrics such as lower RMSE and MAE.

Demonstrates robustness across two large-scale datasets.

Abstract

Soil Organic Carbon (SOC) constitutes a fundamental component of terrestrial ecosystem functionality, playing a pivotal role in nutrient cycling, hydrological balance, and erosion mitigation. Precise mapping of SOC distribution is imperative for the quantification of ecosystem services, notably carbon sequestration and soil fertility enhancement. Digital soil mapping (DSM) leverages statistical models and advanced technologies, including machine learning (ML), to accurately map soil properties, such as SOC, utilizing diverse data sources like satellite imagery, topography, remote sensing indices, and climate series. Within the domain of ML, self-supervised learning (SSL), which exploits unlabeled data, has gained prominence in recent years. This study introduces a novel approach that aims to learn the geographical link between multimodal features via self-supervised contrastive learning, employing pretrained Vision Transformers (ViT) for image inputs and Transformers for climate data, before fine-tuning the model with ground reference samples. The proposed approach has undergone rigorous testing on two distinct large-scale datasets, with results indicating its superiority over traditional supervised learning models, which depends solely on labeled data. Furthermore, through the utilization of various evaluation metrics (e.g., RMSE, MAE, CCC, etc.), the proposed model exhibits higher accuracy when compared to other conventional ML algorithms like random forest and gradient boosting. This model is a robust tool for predicting SOC and contributes to the advancement of DSM techniques, thereby facilitating land management and decision-making processes based on accurate information.