Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sugarcane Health Monitoring With Satellite Spectroscopy and Machine Learning: A Review

Ethan Kane Waters, Carla Chia-Ming Chen, Mostafa Rahimi Azghadi

TL;DR

The paper addresses the need for scalable, early detection of sugarcane health issues across large plantations using remote sensing. It surveys satellite-based spectroscopy (hyperspectral and multispectral) and vegetation-index–driven ML approaches, evaluating their capabilities and limitations for disease and pest detection. Key gaps identified include variety-dependent reflectance, meteorological effects, limited multi-disease detection, lack of cross-method benchmarking, and atmospheric correction constraints, along with trade-offs between satellite and drone-based sensing. The review provides guidance for developing practical, cost-effective large-scale sugarcane health monitoring systems leveraging freely available satellites and advanced analytics.

Abstract

Research into large-scale crop monitoring has flourished due to increased accessibility to satellite imagery. This review delves into previously unexplored and under-explored areas in sugarcane health monitoring and disease/pest detection using satellite-based spectroscopy and Machine Learning (ML). It discusses key considerations in system development, including relevant satellites, vegetation indices, ML methods, factors influencing sugarcane reflectance, optimal growth conditions, common diseases, and traditional detection methods. Many studies highlight how factors like crop age, soil type, viewing angle, water content, recent weather patterns, and sugarcane variety can impact spectral reflectance, affecting the accuracy of health assessments via spectroscopy. However, these variables have not been fully considered in the literature. In addition, the current literature lacks comprehensive comparisons between ML techniques and vegetation indices. We address these gaps in this review. We discuss that, while current findings suggest the potential for an ML-driven satellite spectroscopy system for monitoring sugarcane health, further research is essential. This paper offers a comprehensive analysis of previous research to aid in unlocking this potential and advancing the development of an effective sugarcane health monitoring system using satellite technology.

Sugarcane Health Monitoring With Satellite Spectroscopy and Machine Learning: A Review

TL;DR

The paper addresses the need for scalable, early detection of sugarcane health issues across large plantations using remote sensing. It surveys satellite-based spectroscopy (hyperspectral and multispectral) and vegetation-index–driven ML approaches, evaluating their capabilities and limitations for disease and pest detection. Key gaps identified include variety-dependent reflectance, meteorological effects, limited multi-disease detection, lack of cross-method benchmarking, and atmospheric correction constraints, along with trade-offs between satellite and drone-based sensing. The review provides guidance for developing practical, cost-effective large-scale sugarcane health monitoring systems leveraging freely available satellites and advanced analytics.

Abstract

Research into large-scale crop monitoring has flourished due to increased accessibility to satellite imagery. This review delves into previously unexplored and under-explored areas in sugarcane health monitoring and disease/pest detection using satellite-based spectroscopy and Machine Learning (ML). It discusses key considerations in system development, including relevant satellites, vegetation indices, ML methods, factors influencing sugarcane reflectance, optimal growth conditions, common diseases, and traditional detection methods. Many studies highlight how factors like crop age, soil type, viewing angle, water content, recent weather patterns, and sugarcane variety can impact spectral reflectance, affecting the accuracy of health assessments via spectroscopy. However, these variables have not been fully considered in the literature. In addition, the current literature lacks comprehensive comparisons between ML techniques and vegetation indices. We address these gaps in this review. We discuss that, while current findings suggest the potential for an ML-driven satellite spectroscopy system for monitoring sugarcane health, further research is essential. This paper offers a comprehensive analysis of previous research to aid in unlocking this potential and advancing the development of an effective sugarcane health monitoring system using satellite technology.
Paper Structure (21 sections, 6 figures)

This paper contains 21 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Literature Search Methodology
  3. Sugarcane Health Conditions & Growth Limiting Factors
  4. Sugarcane diseases
  5. Sugarcane pests
  6. Spectral Imagery
  7. Large Scale Spectroscopy
  8. Hyperspectral
  9. Multispectral
  10. Small Scale Spectroscopy
  11. Vegetation Indices
  12. Influential Factors on Sugarcane Reflectance
  13. Sugarcane Variety
  14. Meteorological Effects
  15. Temporal Morphological Changes & Multi-temporal Analysis
  16. ...and 6 more sections

Figures (6)

  • Figure 1: Qualitative relationship between the components necessary to perform sugarcane health monitoring with spectroscopy.
  • Figure 3: Literature Review flow diagram.
  • Figure 4: Sentinel-2 10m spatial resolution true colour image of sugarcane farms in the Herbert region of Queensland, Australia, overlaid with an NDVI raster.
  • Figure 6: NDVI measurements of sugarcane across entire growth cycle with MODIS and HJ-1 CCD remote sensing. Background images indicate approximate season. (Adapted from RN200 with Adobe Photoshop and AI generated artwork)
  • Figure 8: Spatial resolution comparison of available Sentinel-2 resolutions. Sentinel-2 offers four bands at 10m resolution, ten bands at 20m resolution and twelve bands at 60m resolution
  • ...and 1 more figures