A new approach for estimating mangrove canopy cover using Landsat 8 imagery

Monsef, Hesham Abd-El; Smith, Scot E.

doi:10.1016/j.compag.2017.02.007

Cited by 33 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mangrove merupakan ekosistem yang rentan sehingga memerlukan pemantauan yang terus menerus untuk mendeteksi berbagai ancaman seperti kegiatan manusia dan bencana alam. Pemantauan mangrove diperlukan untuk mengukur tingkat pertumbuhan dan mengidentifikasi area yang memerlukan perbaikan (Monsef and Smith, 2017). Penggunaan teknologi penginderaan jauh untuk memantau ekosistem mangrove di Pulau Sebatik belum pernah dilakukan sebelumnya.…”

Section: Pendahuluanunclassified

Studi Kerapatan Dan Perubahan Tutupan Mangrove Menggunakan Citra Satelit Di Pulau Sebatik Kalimantan Utara

Hendrawan

Gaol

Susilo

2018

J. Ilmu dan Teknologi Kelautan Tropis

View full text Add to dashboard Cite

Mangrove forest is a susceptive ecosystem which needs continuous monitoring to detect various threats such as human activities and natural disasters. Remote sensing and geographical information system (GIS) are very effective tools to be used in monitoring mangrove ecosystem due to they can reach large areas and periodically. Application of remote sensing technology to monitor mangrove ecosystem in Sebatik Island had never been conducted before. This research is important to be carried out to reveal changes in condition of mangrove forest in Sebatik Island. Aims of this research were analyzing the correlation between Normalized Different Vegetation Index (NDVI) values and its canopy cover percentages, calculated the accuracy of land cover classification with different spatial resolution, and measuring the changes of mangrove covers from 2005 to 2016. Land cover classification in this research used supervised classification with Maximum Likelihood algorithm. The NDVI was used as mangrove density indicator and vegetation condition. Field data measurement was taken to count canopy cover. The accuracy of Landsat images classification was about 83% and the SPOT 6 images around of 90%. Mangrove forest in Sebatik Island had increased from 2005 to 2016 as high as 31.27%. The correlation between NDVI and canopy percent cover were categorized as high with their coeficient correlation r=0.82 (Landsat 8) and 0.85 (SPOT 6). ABSTRAKHutan mangrove merupakan ekosistem yang rentan sehingga membutuhkan pemantauan terus menerus untuk mendeteksi berbagai ancaman seperti aktivitas manusia dan bencana alam. Pengindraan jauh dan sistem informasi geografis (SIG) merupakan alat yang sangat efektif untuk digunakan dalam pemantauan ekosistem mangrove karena dapat menjangkau daerah yang luas dan dapat dilakukan sekala berkala. Penerapan teknologi pengindraan jauh untuk memantau ekosistem mangrove di Pulau Sebatik belum pernah dilakukan sebelumnya. Penelitian ini penting untuk mengetahui perubahan kondisi hutan mangrove di Pulau Sebatik. Tujuan dari penelitian ini adalah menganalisis korelasi antara nilai Normalized Different Vegetation Index (NDVI) dan persentase tutupan kanopi mangrove, menghitung akurasi klasifikasi tutupan lahan dengan resolusi spasial yang berbeda, dan mengukur perubahan sebaran mangrove dari tahun 2005 sampai 2016. Klasifikasi tutupan lahan dalam penelitian ini menggunakan klasifikasi terbimbing dengan algoritma Maximum Likelihood. NDVI digunakan sebagai indikator kerapatan tutupan mangrove. Pengukuran data lapangan diambil untuk menghitung tutupan kanopi. Penilaian akurasi klasifikasi citra Landsat sekitar 83% dan citra SPOT 6 sekitar 90%. Mangrove di Pulau Sebatik mengalami peningkatan dari tahun 2005 sampai 2016 sebesar 31,27%. Korelasi antara NDVI dan tutupan kanopi dikategorikan tinggi dengan koefisien korelasi r = 0,82 (Landsat 8) dan 0,85 (SPOT 6).

show abstract

Section: Pendahuluanunclassified

Studi Kerapatan Dan Perubahan Tutupan Mangrove Menggunakan Citra Satelit Di Pulau Sebatik Kalimantan Utara

Hendrawan

Gaol

Susilo

2018

J. Ilmu dan Teknologi Kelautan Tropis

View full text Add to dashboard Cite

show abstract

“…High spatial resolution remote sensing imagery with 4 bands (3 bands in the visible and near-infrared bands) performed well at estimating canopy cover variables. Compared to earlier studies on CC estimation in the forest using other types of optical satellite data, the best-case accuracy of GF-2 based CC estimation was equal to or slightly better [6,7,9,30,35]. In this paper, we used the spectral variable and texture content variables derived from GLCM with ensemble models to predict CC and it gave us an encouraging result.…”

Section: Discussionmentioning

confidence: 71%

“…Accordingly, approaches to quickly and efficiently estimate CC, especially over broad areas, is important. Recently, with the development of remote sensing sensors, researchers are interested in mapping regional or global forest canopy cover with various remotely sensed data to provide inputs for land cover monitoring or ecosystem modeling [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Comparison of GF2 and SPOT6 Imagery on Canopy Cover Estimating in Northern Subtropics Forest in China

Zhou

Dian

Wang

et al. 2020

Forests

View full text Add to dashboard Cite

Canopy cover is an important vegetation attribute used for many environmental applications such as defining management objectives, thinning and ecological modeling. However, the estimation of canopy cover from high spatial resolution imagery is still a difficult task due to limited spectral information and the heterogeneous pixel values of the same canopy. In this paper, we compared the capacity of two high spatial resolution sensors (SPOT6 and GF2) using three ensemble learning models (Adaptive Boosting (AdaBoost), Gradient Boosting (GDBoost), and random forest (RF)), to estimate canopy cover (CC) in a Chinese northern subtropics forest. Canopy cover across 97 plots was measured across 41 needle forest plots, 24 broadleaf forest plots, and 32 mixed forest plots. Results showed that (1) the textural features performed more importantly than spectral variables according to the number of variables in the top ten predictors in estimating canopy cover (CC) in both SPOT6 and GF2. Moreover, the vegetation indices in spectral variables had a lower relative importance value than the band reflectance variables. (2) GF2 imagery outperformed SPOT6 imagery in estimating CC when using the ensemble learning model in our data. On average across the models, the R2 was almost 0.08 higher for GF2 over SPOT6. Likewise, the average RMSE and average MAE were 0.002 and 0.01 lower in GF2 than in SPOT6. (3) The ensemble learning model showed good results in estimating CC, yet the different models performed a little differently in the results. Additionally, the GDBoost model performed the best of all the ensemble learning models with R2 = 0.92, root mean square error (RMSE) = 0.001 and mean absolute error (MAE) = 0.022.

show abstract

“…En este proceso se convierte los valores de radiancia a valores de reflectancia, mediante la herramienta FLAASH (Fast Line-ofsight Atmospheric Analysis of Hypercubes) de ENVI 5.3 (Monsef & Smith, 2017), siendo necesario la elevación media de la zona en kilómetros, fecha de toma de imágenes de satélite, ángulo de elevación solar, azimut solar, tipo de sensor y altura del sensor, mostrados en la Tabla 1.…”

Section: Corrección Atmosféricaunclassified

Análisis multi-temporal entre 1975 y 2015 sobre cambios de la cobertura glaciar en los nevados Allin Capac y Chichi Capac, Perú

Aguilar

Larico²,

Laura

et al. 2017

Rev. Investig. Altoandin. - RIA -

View full text Add to dashboard Cite

A new approach for estimating mangrove canopy cover using Landsat 8 imagery

Cited by 33 publications

References 13 publications

Studi Kerapatan Dan Perubahan Tutupan Mangrove Menggunakan Citra Satelit Di Pulau Sebatik Kalimantan Utara

Studi Kerapatan Dan Perubahan Tutupan Mangrove Menggunakan Citra Satelit Di Pulau Sebatik Kalimantan Utara

Comparison of GF2 and SPOT6 Imagery on Canopy Cover Estimating in Northern Subtropics Forest in China

Análisis multi-temporal entre 1975 y 2015 sobre cambios de la cobertura glaciar en los nevados Allin Capac y Chichi Capac, Perú

Contact Info

Product

Resources

About