Integrated sensing and machine learning: Predicting saccharine and bioenergy feedstocks in sugarcane

Predicting saccharine and bioenergy feedstocks in sugarcane enables growers and industries to determine the precise time and location for harvesting a better-quality product in the field. On one hand, Brix, Purity, and total recoverable sugars (TRS) can provide meaningful and reliable indicators of...

Full description

Saved in:

Bibliographic Details
Published in:	Industrial crops and products Vol. 215; p. 118627
Main Authors:	Barbosa Júnior, Marcelo Rodrigues, Moreira, Bruno Rafael de Almeida, Duron, Dulis, Setiyono, Tri, Shiratsuchi, Luciano Shozo, Silva, Rouverson Pereira da
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01-09-2024
Subjects:	1G and 2G bioethanol Active sensor Lignocellulosic content Machine learning Multispectral imagery Sugar content PAR ADF TVD GLI NDVIw CIRE RTK ADL Multispectral imagery SVM UAV PVR DT Lignocellulosic content NDF R MLR TRS 2G Active sensor GCPs MSE ML SPAD SWIR RMSE DOY MAE 1G and 2G bioethanol VI fPAR RF 1G Sugar content Machine learning SDGs SRPI ChlF
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Predicting saccharine and bioenergy feedstocks in sugarcane enables growers and industries to determine the precise time and location for harvesting a better-quality product in the field. On one hand, Brix, Purity, and total recoverable sugars (TRS) can provide meaningful and reliable indicators of high-quality raw materials for first-generation (1 G) bioethanol. Conversely, Cellulose, Hemicellulose, and Lignin are the primary constituents of straw, directly contributing to second-generation (2G) bioethanol. However, analyzing these materials in the laboratory is a time-consuming and non-scalable task. Therefore, we propose an approach based on a multi-sensor framework, which includes multispectral unmanned aerial vehicle (UAV) imagery, thermal, photosynthetic active radiation (PAR), and chlorophyll fluorescence (ChlF) data, along with machine learning (ML) algorithms namely random forest (RF), multiple linear regression (MLR), decision tree (DT), and support vector machine (SVM), to develop a non-invasive and predictive framework for mapping sugarcane feedstocks. We collected samples of stalks and leaves/straw during the maturity stage while simultaneously collecting remote sensing data. The ML models played a crucial role in predicting 1 G (R2 = 0.88–0.93) and 2 G (R2 = 0.56–0.82) feedstocks. Notably, remote sensing data could serve as important features for the models, mainly through the spectral bands (Blue, Green, and RedEdge), DTemp and ChlF. Hence, the best features can be further implemented within a framework to predict sugarcane feedstocks. Our study marks a significant advancement in the industrial-scale prediction of sugarcane feedstocks, providing stakeholders with invaluable prescriptive harvesting strategies for both primary products and by-products. [Display omitted] •1 G and 2 G bioethanol feedstocks were accurately predicted using remote sensing data.•ML algorithms was critical in predicting feedstocks based on the dataset’s behavior.•Blue, Green and RedEdge with DTemp and ChlF were essential for feedstocks’ prediction.•Remote sensing can optimize sugarcane harvest based on feedstocks’ quality.
ISSN:	0926-6690 1872-633X
DOI:	10.1016/j.indcrop.2024.118627