Big data fusion from hyperspectral and LiDAR sensing for fuzzy-logic-based crop condition assessment in precision agriculture

Read full text Summarise with VIRAT
Authors: Sergey Yekimov, Dmitry Nazarov
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Large-scale deployment of sensing technologies in precision agriculture generates heterogeneous data streams that are difficult to integrate into actionable crop condition indicators. This study investigates big data fusion from hyperspectral imaging and light detection and ranging measurements for crop condition assessment based on fuzzy logic. Hyperspectral reflectance provides detailed information on biochemical status, while three-dimensional canopy structure derived from light detection and ranging captures geometry and biomass distribution. A scalable fusion pipeline was implemented to aggregate these data into plot-level indicators and to infer crop condition classes through interpretable fuzzy rules. The system was evaluated in multi-crop field trials using independent yield and plant health measurements as reference. Predictive performance of fuzzy-logic-based fusion was compared with hyperspectral-only and deep learning baselines, and spatial patterns of stress detection were analysed at management zone scale. Results demonstrate that combined spectral–structural information significantly improves condition assessment while preserving transparency and expert interpretability.

Fields of Study & Subjects

Remote Sensing in Agriculture Smart Agriculture and AI Remote Sensing and LiDAR Applications

Publication details

Journal / source
International Scientific Forum on Computer and Energy Sciences (WFCES)
Pages
10–10
Publication date
30 March 2026
Language
EN