Oil palm mapping over Peninsular Malaysia using Google Earth Engine and machine learning algorithms

Shaharum, Nur Shafira Nisa; Shafri, Helmi Zulhaidi Mohd; Ghani, Wan Azlina Wan Ab Karim; Samsatli, Sheila; Al-Habshi, M. M. A.; Yusuf, Badronnisa

doi:10.1016/j.rsase.2020.100287

Cited by 47 publications

(45 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the canopy of young palm oil trees is sparse and the surrounding soil can be a dominant factor in giving reflection towards the satellite, Sentinel C-band radar data was able to differentiate between pure bare land and bare land that has little vegetation on it like young oil palm, due to the C-band's canopy penetration ability [64]. Other studies such as [30] produced a large difference of 31% and [63] a small difference of only 3.2% compared to MPOB's estimation (it should be noted that [63] produced oil palm area estimates for 2017). Bare lands appear dark in radar images because of the surface, having rough and dry soil properties that cause the radar signal to be scattered away from the sensor.…”

Section: Validation Of Oil Palm Mappingmentioning

confidence: 99%

“…We conducted an error analysis by implementing a previously proposed algorithm [23] for Peninsular Malaysia and the results showed that the threshold values for HH-HV and HH/HV polarizations were not able to differentiate oil palm from water, forest, and urban areas for Peninsular Malaysia. A recent study [63] projected the total oil palm areas in Peninsular Malaysia to be 21.14 Mha for year 2017. They employed non-parametric machine learning algorithms such as SVM, CART, and RF using Landsat satellite images on the Google Earth Engine platform.…”

Section: Validation Of Oil Palm Mappingmentioning

confidence: 99%

See 1 more Smart Citation

Synergy of Active and Passive Remote Sensing Data for Effective Mapping of Oil Palm Plantation in Malaysia

Najib

Kanniah

Cracknell

et al. 2020

Forests

View full text Add to dashboard Cite

Oil palm is recognized as a golden crop, as it produces the highest oil yield among oil seed crops. Malaysia is the world’s second largest producer of palm oil; 16% of its land is planted with oil palm. To cope with the ever-increasing global demand on edible oil, additional areas of oil palm are forecast to increase globally by 12 to 19 Mha by 2050. Multisensor remote sensing plays an important role in providing relevant, timely, and accurate information that can be developed into a plantation monitoring system to optimize production and sustainability. The aim of this study was to simultaneously exploit the synthetic aperture radar ALOS PALSAR 2, a form of microwave remote sensing, in combination with visible (red) data from Landsat Thematic Mapper to obtain a holistic view of a plantation. A manipulation of the horizontal–horizontal (HH) and horizontal–vertical (HV) polarizations of ALOS PALSAR data detected oil palm trees and water bodies, while the red spectra L-band from Landsat data (optical) could effectively identify built up areas and vertical–horizontal (VH) polarization from Sentinel C-band data detected bare land. These techniques produced an oil palm area classification with overall accuracies of 98.36% and 0.78 kappa coefficient for Peninsular Malaysia. The total oil palm area in Peninsular Malaysia was estimated to be about 3.48% higher than the value reported by the Malaysian Palm Oil Board. The over estimation may be due the MPOB’s statistics that do not include unregistered small holder oil palm plantations. In this study, we were able to discriminate most of the rubber areas.

show abstract

Section: Validation Of Oil Palm Mappingmentioning

confidence: 99%

Section: Validation Of Oil Palm Mappingmentioning

confidence: 99%

Synergy of Active and Passive Remote Sensing Data for Effective Mapping of Oil Palm Plantation in Malaysia

Najib

Kanniah

Cracknell

et al. 2020

Forests

View full text Add to dashboard Cite

show abstract

“…In [42], several decision level and feature level fusion approaches were developed to tackle the problem of local climate zones classification based on a multitemporal and multimodal dataset, including image (Landsat 8 and Sentinel-2) and vector data (from OpenStreetMap) using ensemble classifiers and deep learning approaches. Finally, in [43] a feature level fusion of information from Google Earth and ML algorithms, including SVMs and regression trees, was proposed for a problem of palm oil mapping in Malaysia.…”

Section: Land Use Applicationsmentioning

confidence: 99%

“…Support Vector Machines [37,43], Random Forests algorithms [37], Regression trees [43], Deep Convolutional Neural Networks [39] in a cellular automata -Markov [40]. [37,38,39,40,41,43].…”

Section: Droughts Eventsmentioning

confidence: 99%

Machine learning information fusion in Earth observation: A comprehensive review of methods, applications and data sources

et al. 2020

View full text Add to dashboard Cite

This paper reviews the most important information fusion data-driven algorithms based on Machine Learning (ML) techniques for problems in Earth observation. Nowadays we observe and model the Earth with a wealth of observations, from a plethora of different sensors, measuring states, fluxes, processes and variables, at unprecedented spatial and temporal resolutions. Earth observation is well equipped with remote sensing systems, mounted on satellites and airborne platforms, but it also involves in-situ observations, numerical models and social media data streams, among other data sources. Data-driven approaches, and ML techniques in particular, are the natural choice to extract significant information from this data deluge. This paper produces a thorough review of the latest work on information fusion for Earth observation, with a practical intention, not only focusing on describing the most relevant previous works in the field, but also the most important Earth observation applications where ML information fusion has obtained significant results. We also review some of the most currently used data sets, models and sources for Earth observation problems, describing their importance and how to obtain the data whether needed. Finally, we illustrate the application of ML data fusion with a representative set of case studies, as well as we discuss and outlook the near future of the field.

show abstract

“…In addition, the selection of machine learning classifiers is fundamental to guarantee the oil palm detection accuracy. These classifiers include support vector machine (SVM) [26], naïve Bayes (NB) classifiers [27], classification and regression trees (CART) [28], and neural networks [29]. However, these classifiers depend on large amounts of sample information to improve the prediction accuracy, and the acquisition of these samples is considerably time-and labor-intensive.…”

Section: Introductionmentioning

confidence: 99%

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

Qian

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

Oil palm mapping over Peninsular Malaysia using Google Earth Engine and machine learning algorithms

Cited by 47 publications

References 45 publications

Synergy of Active and Passive Remote Sensing Data for Effective Mapping of Oil Palm Plantation in Malaysia

Synergy of Active and Passive Remote Sensing Data for Effective Mapping of Oil Palm Plantation in Malaysia

Machine learning information fusion in Earth observation: A comprehensive review of methods, applications and data sources

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

Contact Info

Product

Resources

About