Feature Treatment and Bootstrap Stability in Clustering Orchard Microclimate Time Series
Year: 2026
Type: software
Abstract: Analysis code and reproducibility package for the study "Feature treatment and bootstrap stability in clustering orchard microclimate time series". Aggregates a six-month hourly IoT record from a single durian orchard into daily features, contrasts a naive feature treatment against a physics-informed one that log-damps zero-inflated rain and stress-hour counts, and reports cluster-wise bootstrap Jaccard stability, Markov regime dynamics, dry-spell detection and an FAO-56 vapour-pressure-deficit provenance check.
Authors: Thongnim, Pattharaporn, Srinil, Phaitoon
Institution: Burapha University
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7208726552