Claim Missing Document
Check
Articles

Found 3 Documents
Search

PEMODELAN SPASIAL PREDIKSI LONGSOR DI KECAMATAN MALALAK DAN KECAMATAN IV KOTO, KABUPATEN AGAM DENGAN MACHINE LEARNING RANDOM FOREST Andika Adityawarman; Triyatno
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 10 No. 03 (2025): Volume 10 No. 03 September 2025
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v10i03.31022

Abstract

The objectives of this study are: 1) Spatial modeling of landslide prediction, 2) Analysis of factors that contribute most to landslide occurrence, and 3) Landslide prediction model as a basis for landslide disaster mitigation planning. This study uses a multivariate statistical approach with random forest machine learning, and model validation is performed by calculating the Area Under Curve (AUC) value using the R language. The variables analyzed in this study include landslide locations, slope direction, slope curvature, slope inclination, elevation, rainfall, land cover, geology, soil type, landform, distance from roads, distance from rivers, and vegetation index. The results of the study found 57 landslide locations spread across the study area. The resulting machine learning random forest produced a landslide hazard prediction map with an AUC value of 0.9062, classified into five hazard level categories based on probability values: very low with an area of 5,240.98 hectares (27.64%), low with an area of 4,468.25 hectares (23.56%), moderate with an area of 4,336.05 hectares (22.86%), high with an area of 3,048.19 hectares (16.07%), and very high with an area of 1,870.42 hectares (9.86%). The largest contributing factors to landslides were slope gradient, rainfall, and distance from roads. Mitigation strategies based on the primary contributing factors to landslides include the construction of retaining walls, soil retention structures, drainage improvements, revegetation of slopes with strong root systems, and regular monitoring.
Flood Hazard Mitigation at Tarusan Watershed, South Pesisir District, West Sumatera Province Umar, Iswandi; Triyatno
Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) Vol 14 No 1 (2024): Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (JPSL)
Publisher : Pusat Penelitian Lingkungan Hidup, IPB (PPLH-IPB) dan Program Studi Pengelolaan Sumberdaya Alam dan Lingkungan, IPB (PS. PSL, SPs. IPB)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jpsl.14.1.101-108

Abstract

Floods are the most common natural disasters in Indonesia and have enormous potential. This study aims to determine the flood hazard zone and regional arrangement in the Tarusan Watershed, South Pesisir Regency. To determine the flood hazard zone using the GIS approach. The indicators used to determine flood hazard are slope, rainfall, soil type, landform, geology, and land use. Determine the direction of regional arrangement with an Interpretative Structural Modeling (ISM) approach. The results showed that the high flood hazard zone in the Tarusan watershed is about 22% of the total area, the medium index is around 58%, and the low flood hazard index is 20%. The high - hazard zone of flood disasters in the study area is caused by high rainfall and topographic conditions of the Tarusan Watershed. The main priority in the management of flood - hazard areas in the Tarusan Watershed is to find economic alternatives to reduce forest destruction. Increasing the economic value of the community can lead to reduced community activities in carrying out land conversion, especially in forest areas.
PEMETAAN DAMPAK BENCANA BANJIR BANDANG PADA DAS ANAI : STUDI KASUS KECAMATAN X KOTO DAN PADANG PANJANG BARAT Fitria Rahmi Mardhatillah; Triyatno
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 10 No. 02 (2025): Volume 10 No. 02 Juni 2025 In Press
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v10i02.24528

Abstract

The objectives of this research are: 1) Flash flood hazard mapping, 2) Analysis of infrastructure and land use affected by flash floods. This type of research uses Quantitative descriptive method. The results of the research are: 1) The hazard classification results are divided into 4 classes with an area of very high (240.18 Ha), high (207.22 Ha), low (325.95 Ha), and very low (425.86 Ha) from a total buffer area of 1,199.21 Ha, 2) The results of infrastructure identification affected by flash floods were 273 units out of 1,637, consisting of 233 buildings out of 1,484 buildings, 18 bridges out of 27 bridges, and 22 roads out of 126 roads. Meanwhile, in terms of land use, 702 households were affected, consisting of 396 households in agricultural land ownership, 243 households in ownership of built-up land, and 63 households in ownership of other uses. The land use identified in the buffer area is 427.97 hectares, consisting of 351.09 hectares of agricultural land, 65.04 hectares of built-up land, and 11.84 hectares of other uses. It can be concluded based on the calculation area of the results of the very high and high classification of flash flood hazards, the area of land use affected is 154.05 Ha, consisting of 128.06 Ha of agricultural land, 16.65 Ha of built-up land, and 9.34 Ha of other uses.