A New Machine Learning Approach in Detecting the Oil Palm Plantations Using Remote Sensing Data

Abstract

The rapid expansion of oil palm is a major driver of deforestation and other associated damage to the climate and ecosystem in tropical regions, especially Southeast Asia. It is therefore necessary to precisely detect and monitor oil palm plantations to safeguard the ecosystem services and biodiversity of tropical forests. Compared with optical data, which are vulnerable to cloud cover, the Sentinel-1 dual-polarization C-band synthetic aperture radar (SAR) acquires global observations under all weather conditions and times of day and shows good performance for oil palm detection in the humid tropics. However, because accurately distinguishing mature and young oil palm trees by using optical and SAR data is difficult and considering the strong dependence on the input parameter values when detecting oil palm plantations by employing existing classification algorithms, we propose an innovative method to improve the accuracy of classifying the oil palm type (mature or young) and detecting the oil palm planting area in Sumatra by fusing Landsat-8 and Sentinel-1 images. We extract multitemporal spectral characteristics, SAR backscattering values, vegetation indices, and texture features to establish different feature combinations. Then, we use the random forest algorithm based on improved grid search optimization (IGSO-RF) and select optimal feature subsets to establish a classification model and detect oil palm plantations. Based on the IGSO-RF classifier and optimal features, our method improved the oil palm detection accuracy and obtained the best model performance (OA = 96.08% and kappa = 0.9462). Moreover, the contributions of different features to oil palm detection are different; nevertheless, the optimal feature subset performed the best and demonstrated good potential for the detection of oil palm plantations.

A Review of an Artificial Intelligence Framework for Identifying the Most Effective Palm Oil Prediction

“…In order to improve accuracy, hyperparameter optimisation must be used. Its accuracy was superior to other classifiers, such as SVM, CART, NN, and IGSO-RF classifiers that used the IGSO algorithm to fine-tune the parameters of the traditional RF model [125].…”

“…Traditional ML techniques, classical image processing methods, and deep learning methods can all be used to identify the crowns of trees. RF [125,126] and SVM [111,116] are two of the most commonly used classifiers for tree crown detection in traditional ML approaches. When compared to traditional image processing methods, ML techniques have made significant progress.…”

“…Simultaneous and discrete variables could be used in the RF model, exhibiting an advantage over linear regression models [125]. Nevertheless, the RF variants present several drawbacks.…”

A Review: Progression of Remote Sensing (RS) and Geographical Information System (GIS) Applications in Oil Palm Management and Sustainability

“…For oil palm classification, combining Landsat and SAR data yielded the greatest overall classification accuracy (84%) as well as the highest producer and user accuracy with 84% and 90%, respectively (Sarzynski et al, 2020). In fact, from the same region in different research, the researchers fuse the Landsat-8 and Sentinel-1 images to create alternative feature combinations through extract multitemporal spectral characteristics, SAR backscattering values, vegetation indices, and texture features for their classification and enhancing the accuracy of oil palm recognition and produced the highest model performance (OA = 96.08 % and kappa = 0.9462) (Xu et al, 2021). Next, other research also applied the GIS approach together with CA-Markov prediction to estimate the land changes between oil palm plantation and forestry which bring out the accuracy of 88% from the Kappa Test (Maulidya et al, 2021).…”

A Novel Query Strategy-Based Rank Batch-Mode Active Learning Method for High-Resolution Remote Sensing Image Classification

“…In this study, the classification features included 4 spectral features, 14 vegetation index features, and 192 texture features calculated from 4 spectral bands (Table 3). The texture features of the four spectral bands include eight variables: the mean, variance, homogeneity, contrast, dissimilarity, entropy, angular second moment, and correlation [52][53][54]. There are also different windows: 3 × 3, 5 × 5, 7 × 7, 9 × 9, 11 × 11, and 13 × 13 [55].…”