PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 5, 2026ACM Transactions on Internet of Things0 citationsOpen Access

Data-driven Root Tuber Biomass Estimation via a Wireless Network

View Full Paper
TWTao WangYZYang ZhaoPYPeng Yang

Key Points

  • The aim is to develop a framework for estimating below-ground biomass of root tubers using IoT devices and advanced machine learning techniques.
  • Developed a tuber biomass sensing framework utilizing IoT for non-destructive measurement.
  • Created a dataset with over 700,000 received signal strength measurements.
  • Built a data-driven model using convolution neural networks and attention mechanisms.
  • Employed contrastive learning to enhance feature extraction and reduce bias from imbalanced data.
  • Achieved state-of-the-art performance in biomass estimation.
  • Improved model generalizability and accuracy for varied biomass levels.
  • Demonstrated the effectiveness of the proposed methods through extensive experiments.

Abstract

Below-ground biomass (BGB) of root tubers is an important phenotypic trait in crop monitoring and other agricultural applications. This paper proposes a novel tuber biomass sensing (TBS) framework that uses internet of things (IoT) devices to enable non-destructive estimation of below-ground root tuber biomass. Specifically, we perform extensive experiments to build a new BGB dataset with more than 700,000 received signal strength (RSS) measurements collected by our low-cost wireless network. Then, we propose a novel data-driven model that integrates convolution neural networks, residual connections, and attention mechanisms to facilitate discriminative feature extraction from RSS data and achieve state-of-the-art (SOTA) performance in biomass estimation. In addition, to mitigate performance degradation caused by imbalanced training data, we propose a contrastive learning method that aligns feature representations of samples with similar biomass values while increasing the separation between those with significantly different values. This method reduces estimation bias toward high-frequency biomass labels, thereby improving the performance and generalizability of the data-driven model. Experimental results demonstrate the efficacy of the proposed TBS framework. Our dataset and pre-trained models are publicly available on https://zenodo.org/records/15000852.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/69a91d8dd6127c7a504c067dhttps://doi.org/10.1145/3800586
Ask AI
Helpful
Bookmark
Share
View Full Paper