A low-cost, AI-powered Measurement Verification and Reporting System for growing trees with smallholder farmers

Abstract

Limited access to low-cost tools to measure, report, and verify (MRV) tree growth with smallholder farmers limits the scaling of tree planting efforts in developing countries. Artificial Intelligence (AI) offers the potential for low-cost, reliable, and accessible measurement and verification tools to be developed for an MRV platform to scale tree planting efforts in developing countries. Here, we present an AI-powered non-contact tree diameter measurement and verification tool. We have developed an AI-powered algorithm that accurately estimates the diameter of a tree from an image of the tree with a reference object. This non-contact measurement method utilizes semantic segmentation and image processing techniques to analyze an image of the tree with the reference object. The performance of the proposed method was evaluated on 142 trees with tape-measured diameters at breast height ranging from 5 to 60 cm. A regression analysis between predicted and measured diameter values had an R 2 and an RMSE of 0.97 and 2.23 cm, respectively. Thus, using a smartphone application, the non-contact method developed here can empower anyone to accurately measure and report tree growth by just taking pictures of the trees with the reference object. The images submitted with on-farm measurements serve as data for future verification operations using the AI-powered algorithm. With the reference object serving as a unique tree identifier, a tree’s survival and diameter measurements can be tracked over time. The MRV system described here, with the developed AI-powered non-contact tree diameter measurement and verification tool, can empower organizations to plant, grow, and monitor trees with anyone, including smallholder farmers.

Plant phenotyping relevance

画像から樹木の胸高直径という植物形質を推定するAI・セグメンテーション手法を開発し、実測値との性能検証も行っており、植物フェノタイピング手法が中心である。

Code and data availability

The paper's Data Availability Statement explicitly provides three public, paper-specific assets: the tree image dataset used to calibrate/evaluate the diameter algorithm (ScholarSphere), the statistical analysis data/code repository (GitHub), and the containerized diameter estimation tool (Docker Hub). PixelAnnotationT