Machine Learning Techniques for Phenology Assessment of Sugarcane Using Conjunctive SAR and Optical Data

Abstract

Crop phenology monitoring is a necessary action for precision agriculture. Sentinel-1 and Sentinel-2 satellites provide us with the opportunity to monitor crop phenology at a high spatial resolution with high accuracy. The main objective of this study was to examine the potential of the Sentinel-1 and Sentinel-2 data and their combination for monitoring sugarcane phenological stages and evaluate the temporal behaviour of Sentinel-1 parameters and Sentinel-2 indices. Seven machine learning models, namely logistic regression, decision tree, random forest, artificial neural network, support vector machine, naïve Bayes, and fuzzy rule based systems, were implemented, and their predictive performance was compared. Accuracy, precision, specificity, sensitivity or recall, F score, area under curve of receiver operating characteristic and kappa value were used as performance metrics. The research was carried out in the Indo-Gangetic alluvial plains in the districts of Hisar and Jind, Haryana, India. The Sentinel-1 backscatters and parameters VV, alpha and anisotropy and, among Sentinel-2 indices, normalized difference vegetation index and weighted difference vegetation index were found to be the most important features for predicting sugarcane phenology. The accuracy of models ranged from 40 to 60%, 56 to 84% and 76 to 88% for Sentinel-1 data, Sentinel-2 data and combined data, respectively. Area under the ROC curve and kappa values also supported the supremacy of the combined use of Sentinel-1 and Sentinel-2 data. This study infers that combined Sentinel-1 and Sentinel-2 data are more efficient in predicting sugarcane phenology than Sentinel-1 and Sentinel-2 alone.

A deep learning approach for deriving winter wheat phenology from optical and SAR time series at field level

“…Even if we observed an increase in prediction accuracy over using one of both sensors alone, we could not clearly confirm the findings by Mercier et al (2020), who found an improvement by combining S1 and S2 data for their phenology classification algorithm. This synergy was also suggested by Harfenmeister et al (2021), Veloso et al (2017), andYeasin et al (2022) who found vastly different but also complementary performances of SAR and optical time series for analyzing the phenology of winter wheat, barley and sugarcane. The improvement for some stages could be attributed to uncertainties and ambiguities in the predictions with SAR or optical data alone, respectively, that could be resolved by combining both.…”

“…(2020) and Yeasin et al (2022). Both reported improvements over single-sensor models, supporting the assumption of data complementarity for phenological analyses.…”

“…Both reported improvements over single-sensor models, supporting the assumption of data complementarity for phenological analyses. However, Mercier et al (2020) and Yeasin et al (2022) were based on a limited number of observations, which hampers accurate inferences about the timing of actual stage transitions.…”

Spectrum-Based Logistic Regression Modeling for the Sea Bottom Soil Categorization

“…Application of the logistic regression approach to a wide range of applied tasks is part of the mainstream of geophysical research, especially in marine geophysics [45][46][47][48][49][50][51][52]; for example, this approach is used for the study of changes in soil properties [45], ocean processes [46], etc. However, such an approach is rarely used for soil classification of the sea bottom.…”