Pemetaan Perubahan Penutup Lahan Di Sub-DAS Kreo Menggunakan Machine Learning Pada Google Earth Engine

Fariz, Trida Ridho; Daeni, Fitri; Sultan, Habil

doi:10.21776/ub.jsal.2021.008.02.4

Cited by 8 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hasil tersebut ditampilkan pada Gambar 6. Hasil visualisasi awal citra Sentinel-1 yang telah di pre-processing oleh GEE merupakan tampilan citra komposit yang disediakan oleh ESA [15]. Visualisasi awal yang ditampilkan merupakan Sentinel-1 sebelum dilakukan proses data filtering dan change detection.…”

Section: Hasil Dan Diskusiunclassified

Pemetaan Daerah Rawan Ancaman Banjir di Area Kabupaten Kampar Dengan Menggunakan GEE (Google Earth Engine)

Pratama,

Sutikno,

Yusa

2024

SAINTIS

View full text Add to dashboard Cite

[ID] Kabupaten Kampar merupakan salah satu wilayah yang sering mengalami banjir, yang diakibatkan meluapnya sungai Kampar. Sepanjang tahun 2011 – 2017 tercatat paling sedikit telah terjadi bencana banjir 1 (satu) kali dalam setahun. Untuk meminimalisir dampak kejadian banjir, maka perlu dilakukan mempelajari karakteristik curah hujan secara temporal maupun spasial. Hal ini penting sebagai informasi kepada masyarakat untuk mengantisipasi dampak curah hujan ekstrim pada waktu dan lokasi tertentu. Penelitian ini bertujuan untuk mengindentifikasi spatio-temporal yang ekstrim dari curah hujan di Kabupaten Kampar yang sering menyebabkan banjir. Namun untuk mengidentifikasi ciri – ciri hujan, penelitian ini menggunakan CHIRPS (Climate Hazards InfraRed Precipitation dengan Station) data satelit karena data observasi data curah hujan di Station Klimatologi Riau tidak tersedia 2012. Hasil identifikasi menunjukan bahwa korelasi ( R ) nilai antara data observasi curah hujan dan data satelit CHIRPS adalah 0.526. Nilai ini adalah diartikan “sedang” untuk dijadikan alternatif data kajian. GEE (Google Earth Engine) sebagai platform berbasis cloud digunakan untuk mengidentifikasi karakteristik temporal diketahui curah hujan ekstrim terjadi di bulan Januari, Juni, Agustus dan November. Hasil identifikasi spasial menunjukan bahwa wilayah tersebut mempunyai rata – rata curah hujan maksimum tertinggi terdapat di wilayah Kecamatan Koto Kampar Hulu 40.01 mm/hari. Ini dapat dipastikan dengan melihat dokumentasi kejadian banjir yang sering terjadi di wilayah tersebut. [EN] Kampar Regency is one of the areas that frequently experiences flooding, which is caused by the overflowing of the Kampar River. Throughout 2011 - 2017, it was recorded that at least 1 (one) flood disaster occurred a year. To minimize the impact of flood events, it is necessary to study the characteristics of rainfall both temporally and spatially. This is important as information for the public to anticipate the impact of extreme rainfall at certain times and locations. This research aims to identify spatio-temporal extremes of rainfall in Kampar Regency which often cause flooding. However, to identify the characteristics of rainfall, this research uses CHIRPS (Climate Hazards InfraRed Precipitation with Station) satellite data because rainfall observation data at the Riau Climatology Station is not available in 2012. The identification results show that the correlation (R) value between rainfall observation data and CHIRPS satellite data is 0.526. This value is interpreted as "medium" to be used as an alternative study data. GEE (Google Earth Engine) as a cloud-based platform is used to identify the known temporal characteristics of extreme rainfall occurring in January, June, August and November. The spatial identification results show that this area has the highest average maximum rainfall in the Koto Kampar Hulu District area of 40.01 mm/day. This can be confirmed by looking at the documentation of flood events that often occur in the area.

show abstract

Section: Hasil Dan Diskusiunclassified

Pemetaan Daerah Rawan Ancaman Banjir di Area Kabupaten Kampar Dengan Menggunakan GEE (Google Earth Engine)

Pratama,

Sutikno,

Yusa

2024

SAINTIS

View full text Add to dashboard Cite

show abstract

“…Aktivitas manusia di daerah tangkapan air seperti pemupukan, pemakaian pestisida, dan humus akan terakumulasi di badan air [18]. Pengelolaan kualitas badan air tidak hanya dilakukan di badan air, tetapi harus dilakukan juga di daerah tangkapan airnya karena terdapat hubungan erat [19,20].…”

Section: Hasil Dan Pembahasanunclassified

Perbandingan Mutu Air di Bendungan yang Berada di Provinsi Jawa Timur

Wardhani,

Irmansyah,

Oktaviani

et al. 2023

JSE

View full text Add to dashboard Cite

A dam is a body of water that is relied upon in raw water supply. Many dams have deteriorated due to human activities in their catchment areas. East Java Province Government is currently trying to improve the function of the dam as a water reserve in the dry season. This study aims to compare water quality in nine dams located in East Java Province. The Telaga Pasir and Gonggang Dams are in Magetan Regency. The Notopuro, Saradan, Kedung Brubus, and Dawuhan dams are in Madiun Regency. Kedung Bendo, Pondok, and Sangiran dams are in Ngawi Regency. The method for determining water quality is based on KepMenLH No 115/2003 concerning guidelines for determining water quality status. Water sampling was carried out on January 24 to February 7, 2022, representing the dry season by grab sampling. Water samples were taken from the part of the dam with a pool of water. The results showed that the water quality of all dams was categorized as good to slightly polluted, with index values ranging from 0.80 to 3.10. The cause of water quality being lightly polluted is the BOD, COD, Free Chlorine, Arsenic, Cadmium, Copper, Ammonia, and Nitrite, which do not meet quality standards. The presence of these parameters is predicted to originate from the activities of residents around the catchment area, such as settlements and agriculture.

show abstract

“…GEE can also explore web applications for data catalog exploration, visualization, and fundamental analysis that allows users to carry out simple analyses [20] The use of GEE for remote sensing has been widely carried out, especially for land use and land cover analysis, as was done by [21] using machine learning (ML) in the form of support vector machines (SVM), random forest (RF) and classification and regression trees (CART) in analyzing land use and land cover in the Munneru River Basin, India. Other research regarding LULC analysis was carried out by [19], [22], [23], [24], [25], and [26], and mangrove mapping was carried out by [27]. Several ML studies were conducted on GEE on oil palm plants by [28], who used several satellite sensors to map oil palms.…”

Section: Introductionmentioning

confidence: 99%

Mapping the nutrient content of oil palm leaves based on machine learning to determine fertilizer recommendations in North Sumatra

Wiratmoko,

Tengku,

Minasny

et al. 2024

Eighth Geoinformation Science Symposium 2023: Geoinformation Science for Sustainable Planet

View full text Add to dashboard Cite

Oil palm is an essential commodity for Indonesia, which generated USD 28.72 billion in foreign exchange in 2021. This commodity has a history for North Sumatra since the beginning of the oil palm industry, where the origins of the palm oil industry were in the province of North Sumatra. The importance of oil palm for the economy in North Sumatra can be seen from the production of palm oil in the region which fourth ranks in the national palm oil production. The success of oil palm cultivation is strongly influenced by various production factors, one of which is fertilization activities to replace the lost nutrients through harvest or other activities. Accuracy in fertilizing activities is the primary key to the success of oil palm production. Determining the fertilization dosage for oil palm plants currently requires high costs and a relatively long time because it requires leaf analysis in the laboratory. Mapping oil palm leaf nutrients through satellite imagery, especially Landsat-8 imagery, is one of the non-destructive alternative steps to determine the nutrient content of oil palm leaves quickly and precisely. This study aims to map and classify the nutrient condition of oil palm leaves as a reference for preparing the correct dosage of fertilization recommendations in the North Sumatra region. The methods used in this study are three types of classification using machine learning, namely classification and regression tree (CART), random forest (RF), and support vector machine (SVM). The classification results of the three types of machine learning have a high accuracy in classifying or mapping oil palm leaf nutrients in North Sumatra, which is then followed by calculating doses based on plant-transported nutrients and nutrient availability in oil palm leaves. Based on this, the three-machine learning have the potential to provide information quickly on the nutrient content of oil palm leaves.

show abstract

Pemetaan Perubahan Penutup Lahan Di Sub-DAS Kreo Menggunakan Machine Learning Pada Google Earth Engine

Cited by 8 publications

References 7 publications

Pemetaan Daerah Rawan Ancaman Banjir di Area Kabupaten Kampar Dengan Menggunakan GEE (Google Earth Engine)

Pemetaan Daerah Rawan Ancaman Banjir di Area Kabupaten Kampar Dengan Menggunakan GEE (Google Earth Engine)

Perbandingan Mutu Air di Bendungan yang Berada di Provinsi Jawa Timur

Mapping the nutrient content of oil palm leaves based on machine learning to determine fertilizer recommendations in North Sumatra

Contact Info

Product

Resources

About