Mapping mangrove forest using Landsat 8 to support estimation of land-based emissions in Kenya

Kenduiywo, Benson Kipkemboi; Mutua, Felix Nzive; Ngigi, Thomas G.; Waithaka, Edward Hunja

doi:10.1007/s40808-020-00778-x

Cited by 4 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image classification using a supervised machine learning approach requires training and validation data in order to train and test the algorithm's accuracy [37]. In existing research on mangrove classification, training and validation data are obtained through various methods, including field surveys (using GPS), sourced from local authorities, and interpreted visually from high-resolution images such as Google Earth, aerial photographs/UAV, SPOT 6/7, and WorldView-2, supported or supervised by the knowledge of researchers and experts.…”

Section: Reference Datamentioning

confidence: 99%

Studying How Machine Learning Maps Mangroves in Moderate-Resolution Satellite Images

Ambarwari,

Husni

2023

IJAIDM

View full text Add to dashboard Cite

Intertidal mangrove forests are ecosystems that are extremely productive offering diverse socio-economic advantages. Preserving and appropriately using these ecosystems is crucial. However, safeguarding and restoring mangroves present challenges due to their extensive and hard-to-reach areas. Leveraging remote sensing technology and diverse image classification methods has shown promise in accurately mapping and monitoring mangroves. This study reviews the use of machine learning methods in mapping and monitoring mangroves, particularly using moderate-resolution multispectral satellite images. The literature study was conducted by systematically searching and analyzing articles published in Scopus-indexed journals from 2018 and 2023. The primary goals are to uncover methodologies for mapping mangroves with moderate-resolution imagery, identify advancements in machine learning algorithms, and assist researchers in staying updated in this field. The findings reveal that various machine-learning algorithms can be employed to map mangroves. Mangrove mapping with machine learning typically involves stages such as inputting multispectral images, image preprocessing, image classification, and assessing accuracy. Among the techniques, in the case of remote sensing data, ensemble tree-based approaches such as random forest outperform single classifiers. Potential and emerging issues for future research encompass automating the generation of training datasets for specific land cover classification, developing methods to transfer the classification model to different study areas, and making use of cloud-based technologies for processing remote sensing data.

show abstract

Section: Reference Datamentioning

confidence: 99%

Studying How Machine Learning Maps Mangroves in Moderate-Resolution Satellite Images

Ambarwari,

Husni

2023

IJAIDM

View full text Add to dashboard Cite

show abstract

“…Jauh dan perkembangan teknologi satelit berperan sangat signifikan dalam pemetaan tutupan lahan di suatu kawasan (Altamirano et al, 2010;Kenduiywo et al, 2020). Penginderaan jauh memberikan banyak keuntungan dibandingkan survei lapangan dalam memantau ekosistem pesisir ini, selain itu metodenya akurat, cepat dan hemat biaya (Jia et al, 2014), karena kapasitas melakukan perekaman cakupan secara berulang dengan sensor terkalibrasi, multi-resolusi, multispektral, skala besar, jangka panjang, dan hemat biaya untuk pemetaan dan pemantauan perubahan mangrove secara berkala ( D'Iorio et al, 2007;Cissell & Steinberg, 2019;Roy et al, 2019;Sharifi et al, 2022).…”

Section: Penginderaanunclassified

Pemetaan Dinamika Perubahan Tutupan Kawasan Mangrove Berbasis Pendekatan Komputasi Awan di Teluk Pacitan

Hasrul,

Khakhim,

Suadi

2023

hidropilar

View full text Add to dashboard Cite

Mangrove sebagai kawasan yang dicirikan sebagai lahan basah di wilayah intertidal di sepanjang garis pantai memiliki peran penting bagi kehidupan dan penghidupan manusia karena layanan yang diberikannya sebagai daerah pemijahan ikan (nursery ground), tempat mencari makan (feeding ground), daerah pentangkapan ikan (fishing ground), serta cagar alam, retensi sedimen dan pelindung alami terhadap berbagai bencana alam seperti siklon dan tsunami. Peran penting tersebut belum terjaga dengan memadai sehingga dibeberapa lokasi di belahan bumi kawasan mangrove mengalami penyusutan akibat proses antropogenik maupun perubahan lingkungan global. Monitoring secara berkala diperlukan untuk menjaga ekosistem mangrove. Penginderaan jauh menjadi metode yang efektif dalam memetakan areal mangrove secara cepat dan efisien, terutama dengan berkembangnya teknologi pemetaan berbasis komputasi awan (cloud computing). Melalui perangkat google earth engine (GEE) artikel ini melakukan studi di Teluk Pacitan dengan ekstraksi terhadap luasan tutupan mangrove pada tahun 2016 sampai dengan 2022 menggunakan citra satelit Sentinel-2 MSI Level-2A, dengan menggunakan algoritma random forest. Luasan mangrove yang dapat diekstraksi adalah 0,57 Hektar di tahun 2016 dan meningkat menjadi 2,2 hektar di tahun 2022. Berdasarkan sampel yang digunakan, dipilih 80% dari total sampel digunakan untuk training, dan 20% untuk testing. Berdasarkan hasil perhitungan Validation overall accuracy, hasil ekstraksi tahun 2016 mencapai nilai 0,996, dan pada tahun 2022 mencapai nilai 0,966.

show abstract

“…Its outputs are a classified change map with the 12 classes, a corresponding probability map and an updated cloudfree image composite in which the latest cloud-free pixels are replacing the previous pixels in the composite. During this process, a forest mask based on the SLEEK land cover map for the year 2016 (Kenduiywo et al, 2020) is used to filter out any non-forest locations. When the Pyeo forest cover loss alerts are received by the Forest Information Centre of the Kenya Forest Service in Nairobi, an interpreter checks the quality of the alerts for any erroneous detections.…”

Section: Nrt Change Detectionmentioning

confidence: 99%

Pyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning

Roberts

Mwangi

Mukabi

et al. 2022

Computers & Geosciences

View full text Add to dashboard Cite

Mapping mangrove forest using Landsat 8 to support estimation of land-based emissions in Kenya

Cited by 4 publications

References 49 publications

Studying How Machine Learning Maps Mangroves in Moderate-Resolution Satellite Images

Studying How Machine Learning Maps Mangroves in Moderate-Resolution Satellite Images

Pemetaan Dinamika Perubahan Tutupan Kawasan Mangrove Berbasis Pendekatan Komputasi Awan di Teluk Pacitan

Pyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning

Contact Info

Product

Resources

About