Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Journal of Water and Land Development

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Hybrid machine learning for flood prediction: comparing CHIRPS satellite and ground station data

Rachmawardani Agustina, Kurniawan Budhy, Wijaya Sastra Kusuma, Sopaheluwakan Ardhasena, Sinambela Marzuki

Journal of Water and Land Development

2025

no. 64

87--99

Flooding in Jakarta is a multifaceted issue influenced by a combination of geographical, social, economic, and environmental factors. This study focuses on predicting floods by comparing automatic rain gauge (ARG) ground station data and Climate Hazards Group InfraRed Precipitation (CHIRPS) satellite data using the Adaptive Neurofuzzy Inference System (ANFIS) integrated with principal component analysis (PCA). The dataset includes precipitation measurements from both ARG and CHIRPS along with water level data spanning from 2014 to 2020. ARG provides precise local rainfall data, while CHIRPS offers extensive regional precipitation coverage. To enhance data quality, preprocessing techniques such as mean imputation, data normalisation, and the interquartile range (IQR) method were employed. The ANFIS-PCA model, which integrates fuzzy logic and neural network training, was applied using an 80:20 split for training and validation. When trained with ARG ground station data and water level measurements, the ANFIS-PCA model demonstrated superior accuracy, achieving a root mean square error (RMSE) of 0.13, mean absolute error (MAE) of 0.12, and R2 of 0.82. In contrast, the ANFIS model without PCA yielded higher errors, with RMSE 6.3, MAE 6.2, and R2 0.74. Training with CHIRPS satellite data resulted in significantly higher errors (RMSE 30.14, MAE 24.05, R2 0.42). These findings underscore the superiority of ground-based measurements for flood prediction, given the reduced precision and higher susceptibility to errors in satellite-derived data. While CHIRPS satellite data offers broader spatial coverage, its limitation in precision and higher susceptibility to errors reduce its effectiveness for accurate flood prediction.

Spatial evaluation rainfall estimation on weather radar using Marshall-Palmer reflectivity-rainfall rate in Banten

Hartanto, Humaidi Syahrul, Frida Erna, Ananda Naufal, Sinambela Marzuki

Journal of Water and Land Development

2024

no. 62

193--200

Based on data from the National Disaster Management Agency (Ind.: Badan Nasional Penanggulangan Bencana - BNPB), throughout 2022, more than 91% of disaster events were hydrometeorological disasters, with floods at 43% and landslides at 17%. One of the factors for floods and landslides is high rainfall intensity. Automatic rain gauge (ARG) is a rainfall observation instrument that can accurately measure rainfall at observation points. However, it has problems such as communication systems that cause delays in data transmission, low instrument density, and inability to cover a wide spatial area, which can affect the accuracy of rainfall information. Weather radar is a remote sensing instrument that can estimate rainfall spatially so that weather radar observations can reach areas of the region that do not have ARG. However, before being used as rainfall information, estimation rainfall needs to be evaluated or calibrated. Evaluation of rainfall estimation on weather radar to ARG in Banten at a 30-120 km distance range, shows a coefficient of determination above 0.8. Based on the studies that have been conducted, increase of root mean square error (RMSE) is due to influence of radar observation range and observation distance on ARG. Adjustment of rainfall estimation improves the accuracy of rainfall estimation. Adjusting rainfall estimation can reduce RMSE by 50%.