UAV imagery data and machine learning: A driving merger for predictive analysis of qualitative yield in sugarcane
Данные UAV-съёмки и машинное обучение: движущееся слияние для предиктивного анализа качественного урожая сахарного тростника
2023-01-26
SCID: 54.1/mf67pt25
Discuss with AI
Analytical Purity (Purity)Decision tree (DT)Growing degree days (GDD)Machine learningMultiple linear regression (MLR)Predictive analysisRandom forest (RF)Spectral bandsSugarcane yield qualitySupport vector machine (SVM)UAV imageryVegetation indices°Brix prediction
Figures from the paper
Abstract (AI)
Predicting sugarcane yield by quality allows stakeholders from research centers to industries to decide on the precise time and place to harvest a product on the field; hence, it can streamline workflow while leveling up the cost-effectiveness of full-scale production. °Brix and Purity can offer significant and reliable indicators of high-quality raw material for industrial processing for food and fuel. However, their analysis in a relevant laboratory can be costly, time-consuming, and not scalable. We, therefore, analyzed whether merging multispectral images and machine learning (ML) algorithms can develop a non-invasive, predictive framework to map canopy reflectance to °Brix and Purity. We acquired multispectral images data of a sugarcane-producing area via unmanned aerial vehicle (UAV) while determining °Brix and analytical Purity from juice in a routine laboratory. We then tested a suite of ML algorithms, namely multiple linear regression (MLR), random forest (RF), decision tree (DT), and support vector machine (SVM) for adequacy and complexity in predicting °Brix and Purity upon single spectral bands, vegetation indices (VIs), and growing degree days (GDD). We obtained evidence for biophysical functions accurately predicting °Brix and Purity. Those can bring at least 80% of adequacy to the modeling. Therefore, our study represents progress in assessing and monitoring sugarcane on an industrial scale. Our insights can offer stakeholders possibilities to develop prescriptive harvesting and resource-effective, high-performance manufacturing lines for by-products.
Key Findings
1
Biophysical functions derived from the data accurately predict °Brix and Purity, achieving at least 80% adequacy in modeling.
2
Multiple ML algorithms (MLR, RF, DT, SVM) were tested for adequacy and complexity in predicting °Brix and Purity from UAV-derived data.
3
The approach enables industrial-scale assessment and monitoring of sugarcane, supporting prescriptive harvesting and resource-efficient manufacturing decisions.
4
UAV imagery combined with machine learning can predict sugarcane juice °Brix and analytical Purity using spectral bands, vegetation indices, and growing degree days.
Research Object
UAV imagery data of sugarcane (single spectral bands and vegetation indices) combined with growing degree days
Research Subject
Predictive modeling of qualitative yield indicators (°Brix and analytical Purity of sugarcane juice) using machine learning algorithms (MLR, RF, DT, SVM) based on UAV spectral bands, VIs and GDD
Publication Details
Publication Date
2023-01-26
Journal
Publisher
ISSN
Cited by
14
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest