SoilNet: A Multimodal Multitask Model for Hierarchical Classification of Soil Horizons
Vipin Singh, Teodor Chiaburu, Einar Eberhardt, Stefan Broda, Joey Pr\"ussing, Frank Hau{\ss}er, Felix Bie{\ss}mann

TL;DR
SoilNet is a multimodal, hierarchical classification model that accurately predicts soil horizons by integrating image data and metadata, matching or surpassing expert performance, and offering transparency in complex soil analysis tasks.
Contribution
This work introduces SoilNet, a structured, transparent multimodal multitask model specifically designed for hierarchical soil horizon classification, addressing challenges of complex label structures and data imbalance.
Findings
SoilNet achieves accuracy comparable to or better than human experts.
The model effectively handles complex hierarchical and imbalanced label structures.
User studies confirm the model's practical utility and reliability.
Abstract
Recent advances in artificial intelligence (AI), in particular foundation models, have improved the state of the art in many application domains including geosciences. Some specific problems, however, could not benefit from this progress yet. Soil horizon classification, for instance, remains challenging because of its multimodal and multitask characteristics and a complex hierarchically structured label taxonomy. Accurate classification of soil horizons is crucial for monitoring soil condition. In this work, we propose \textit{SoilNet} - a multimodal multitask model to tackle this problem through a structured modularized pipeline. In contrast to omnipurpose AI foundation models, our approach is designed to be inherently transparent by following the task structure human experts developed for solving this challenging annotation task. The proposed approach integrates image data and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
