Article Per Year (5 Year)
p-Index From 2021 - 2026
1.288
P-Index
This Author published in this journals
All Journal Agromet Indonesian Journal of Geography Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Sumberdaya Lahan Journal of Mathematical and Fundamental Sciences Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) LIMNOTEK - Perairan Darat Tropis di Indonesia International Journal of Remote Sensing and Earth Sciences (IJReSES) JURNAL METEOROLOGI DAN GEOFISIKA Indonesian Journal of Electrical Engineering and Computer Science Jurnal Sumberdaya Lahan Jurnal Tanah dan Iklim Jurnal Meteorologi dan Geofisika The International Journal of Remote Sensing and Earth Sciences (IJReSES)
Akhmad Faqih
Agrometeorology Division, Department Of Geophysics And Meteorology, Faculty Of Mathematics And Natural Sciences, IPB University, Campus IPB Dramaga, Indonesia
Agriculture, Biological Sciences & Forestry Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Earth & Planetary Sciences Energy Environmental Science Mathematics Physics

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Downscaling Modeling Using Support Vector Regression for Rainfall Prediction Sanusi Sanusi; Agus Buono; Imas S Sitanggang; Akhmad Faqih
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 8: August 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i8.pp6423-6430

Abstract

Statistical downscaling is an effort to link global scale to local scale variable. It uses GCM model which usually used as a prime instrument in learning system of various climate. The purpose of this study is as a SD model by using SVR in order to predict the rainfall in dry season; a case study at Indramayu. Through the model of SD, SVR is created with linear kernel and RBF kernel. The results showed that the GCM models can be used to predict rainfall in the dry season. The best SVR model is obtained at Cikedung rain station in a linear kernel function with correlation 0.744 and RMSE 23.937, while the minimum prediction result is gained at Cidempet rain station with correlation 0.401 and RMSE 36.964. This accuracy is still not high, the selection of parameter values for each kernel function need to be done with other optimization techniques.
Optimization of Support Vector Regression using Genetic Algorithm and Particle Swarm Optimization for Rainfall Prediction in Dry Season Gita Adhani; Agus Buono; Akhmad Faqih
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 11: November 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i11.pp7912-7919

Abstract

Support Vector Regression (SVR) is Support Vector Machine (SVM) is used for regression case. Regression method is one of prediction season method has been commonly used. SVR process requires kernel functions to transform the non-linear inputs into a high dimensional feature space. This research was conducted to predict rainfall in the dry season at 15 weather stations in Indramayu district. The basic method used in this study was Support Vector Regression (SVR) optimized by a hybrid algorithm GAPSO (Genetic Algorithm and Particle Swarm Optimization). SVR models created using Radial Basis Function (RBF) kernel. This hybrid technique incorporates concepts from GA and PSO and creates individuals new generation not only by crossover and mutation operation in GA, but also through the process of PSO. Predictors used were Indian Ocean Dipole (IOD) and NINO3.4 Sea Surface Temperature Anomaly (SSTA) data. This research obtained an SVR model with the highest correlation coefficient of 0.87 and NRMSE error value of 11.53 at Bulak station. Cikedung station has the lowest NMRSE error value of 0.78 and the correlation coefficient of 9.01.
An Application of Deep Learning Technique to Improve Subseasonal to Seasonal Rainfall Forecast over Java Island, Indonesia Adyaksa Budi Raharja; Akhmad Faqih; Amsari Mudzakir Setiawan
Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) Vol 12 No 4 (2022): 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.12.4.587-598

Abstract

Subseasonal to seasonal (S2S) rainfall forecast can benefit several sectors, such as water resources, hazard management, and agriculture. However, the forecast remains challenging due to its lack of skill. This study applies Convolutional AutoEncoders (ConvAE), a deep learning technique, to improve the quality of the S2S rainfall forecast. Seven S2S model output incorporated with Subseasonal Experiments Projects (SubX), including CCSM4, CFSv2, FIMr1p1, GEFS, GEOS_v2p1, GEPS6, and NESM, are corrected using the ConvAE approach. We combine 407 ground observations and the CHIRPS dataset using regression kriging methods producing gridded daily precipitation data with 0.05° spatial resolution. We utilize this dataset as a label to train ConvAE models and to perform bias corrections to all members of the SubX forecasts data. The results show that ConvAE is able to increase the quality of weekly S2S rainfall forecasts over Java, Indonesia. The Correlation Coefficient for 1 – 4 weeks lead time are improved from: 0.76, 0.715, 0.692 and 0.722 towards 0.809, 0.751, 0.719 and 0.74, respectively. Furthermore, the average CRPSS improves between 20 – 30% for all lead times.
Sea Surface Temperature Anomaly Characteristics Affecting Rainfall in Western Java, Indonesia Qurrata A'yun Kartika; Akhmad Faqih; I Putu Santikayasa; Amsari Mudzakir Setiawan
Agromet Vol. 37 No. 1 (2023): JUNE 2023
Publisher : PERHIMPI (Indonesian Association of Agricultural Meteorology)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/j.agromet.37.1.54-65

Abstract

Western Java is densely populated with high socio-economic activity. Climate-related disasters can be mitigated with the support of an understanding of systems that produce reliable climate predictions. One of the climate variables included in hydrometeorological disasters is rainfall. The characteristics of rainfall in Western Java cannot be separated from the sea surface temperature (SST) around the area. This study compares the relationship between SST and rainfall with singular value decomposition (SVD) and compares it with Pearson's correlation. SVD Model performance was evaluated using square covariance fraction (SCF) and Pearson correlation. The results showed that rainfall has a higher correlation with SST Anomaly (SSTA) by using SVD, with a correlation of about 0.63 in 6 to 9 months without lag time. Rainfall in western Java was closely related to the positive SSTA anomaly in southern Indonesia, especially the waters south of Java Island, and negative anomalies in other areas. Furthermore, atmospheric dynamic analysis showed that the positive coefficient expansion is followed by warmer SST, lower surface air pressure, higher water vapor, and higher rainfall, all were respective to their normal conditions around western Java. This study concludes that warmer SSTA around Western Java causes increased rainfall in western Java than normal and potentially impacts the hydrological disaster in West Java.
ANALISIS MODEL PREDIKSI AWAL MUSIM HUJAN DI SULAWESI SELATAN Alimatul Rahim; Rini Hidayati; Akhmad Faqih; Mamenun Mamenun
Jurnal Meteorologi dan Geofisika Vol. 16 No. 2 (2015)
Publisher : Pusat Penelitian dan Pengembangan BMKG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31172/jmg.v16i2.269

Abstract

Model prediksi awal musim hujan merupakan salah satu kunci yang dapat digunakan untuk mengurangi resiko kegagalan panen padi yang disebabkan oleh faktor iklim di provinsi Sulawesi Selatan. Model prediksi awal musim hujan dibangun  dengan menggunakan data curah hujan observasi Sulawesi Selatan dan anomali suhu muka laut di kawasan Pasifik dan perairan Sulawesi. Pada studi ini dilakukan analisis pemilihan stasiun hujan observasi, penentuan awal musim hujan, analisis komponen utama dan pengelompokan, analisis korelasi awal musim hujan terhadap anomali suhu muka laut, pembangunan model untuk prediksi awal musimhujan dan verifikasi model.Hasil analisis awal musim hujan menunjukkan setiap stasiun hujan mempunyai perbedaan awal musim hujan dengan rata-rata jatuh pada Julian Date (JD) ke-348 (14 Desember). Berdasarkan hasil analisis PCA dan cluster, diperoleh bahwa di Sulawesi Selatan terbagi menjadi 3 cluster wilayah. Cluster 1 mempunyai pola hujan lokal, sedangkan cluster 2 dan 3 mempunyai pola hujan monsun. Pada peta korelasi antara awal musim hujan di Sulawesi Selatan dan anomali suhu muka laut menunjukkan bahwa terdapat korelasi nyata(r≥0.5) antara kawasan Pasifik dan Laut Sulawesi pada cluster 1 dan 2 pada bulan Juni Juli Agustus September(JJAS). Sedangkan pada cluster 3, korelasi nyata hanya pada bulan Juni di perairan Sulawesi. Model prediksi AMH terbaik, pada cluster 2 terdapat di domain prediktor kawasan pasifik dengan nilai r=0.82, sedangkan pada cluster 1 dan 3, terdapat di domain perairan Sulawesi dengan nilai r=0.78 dan r-0.48. Verifikasi model terpilih pada cluster 3 mempunyai RMSE = 3, sedangkan cluster 1 dan 2, nilai RMSE berturut-turut sebesar 16 dan 29. Model prediction of rainy season onset is one of the keys to reduce the risk of paddy harvest failure because of the climate factor in South Sulawesi province. The model prediction for rainy season onset was build using rainfall data in South Sulawesi and SST anomaly in the Pacific Ocean and Sulawesi Sea. This research is conducted to select the rainfall station, determine onset using rainfall data, analyze PCA and cluster, make a correlation between onset and SST anomaly, develop onset model prediction, and verify the selected model. The onset analysis showed that every rainfall stations have different onset with average is on the 348th of Julian Date (December 14th). Based on the PCA and cluster analysis, there were three clusters of rainfall regions. Cluster 1 has a local pattern, Cluster 2 and 3 have a monsoonal pattern. On the map of correlation between onset in South Sulawesi and SST anomaly showed that there were strong correlations with the Pacific Ocean and Sulawesi Sea in clusters 1 and 2 on JJAS. Moreover, it has a weak correlation in cluster 3 in June in the Sulawesi Sea. The best AMH model prediction for cluster 2 was on the Pacific Ocean domain with r=0.82, on cluster 1 dan 3 was on the Sulawesi sea with r=0.78 and r=0.48. The selected model verification showed that the smallest RMSE (RMSE=3) was on cluster 3, moreover, on clusters 1 and 2, the RMSE model was 16 and 29. 
KARAKTERISTIK SPASIAL DAN TEMPORAL HOTSPOT DI PULAU SUMATERA Mulyono R. Prabowo; Yonny Koesmaryono; Akhmad Faqih; Ardhasena Sopaheluwakan
Jurnal Meteorologi dan Geofisika Vol. 21 No. 1 (2020)
Publisher : Pusat Penelitian dan Pengembangan BMKG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31172/jmg.v21i1.674

Abstract

Kebakaran hutan di Indonesia telah menjadi masalah global yang terjadi setiap tahun, terutama di Pulau Sumatra. Identifikasi kebakaran hutan dan lahan dalam penelitian ini didasarkan pada jumlah dan distribusi hotspot, berdasarkan data citra satelit dari Moderate Resolution Imaging Spectroradiometer (MODIS) pada 2009-2018. Investigasi pada kondisi meteorologi juga didasarkan pada faktor-faktor global dari data Oceanic Nino Index (ONI), Dipole Mode Index (DMI) dan berdasarkan pada indeks kekeringan dari data Standardized Precipitation Index (SPI). Metode yang digunakan adalah metode analisis spasial dan temporal. Tujuan dari penelitian ini adalah untuk mengetahui karakteristik pola distribusi hotspot di Pulau Sumatra, baik secara spasial dan temporal. Ada perbedaan karakteristik spasial dan temporal dari distribusi hotspot di pulau Sumatra, yang didasarkan pada karakteristik topografi, fase ENSO, serta periode musim hujan dan kemarau. Hujan orografis yang terjadi akibat topografi gunung di Aceh dan pantai barat Sumatra mengakibatkan berkurangnya titik api di daerah tersebut. Sementara itu, El Nino meningkatkan jumlah hotspot, sedangkan La Nina mengurangi jumlah hotspot. Dibandingkan dengan IOD, ENSO lebih berpengaruh pada terjadinya peristiwa hotspot di pulau Sumatra. Perbedaan periode musim kemarau di Sumatera utara, tengah, dan selatan juga memberikan perbedaan waktu terjadinya hotspot maksimum di Sumatera. Pola distribusi hotspot di Sumatera utara dan tengah memuncak pada bulan Februari dan Juni, sedangkan di selatan pada bulan September. Konsentrasi titik api yang tinggi (> 50 kejadian perbulan) pada umumnya terjadi di lahan gambut, yang umumnya ditemukan di Sumatra timur (Sumatera Utara, Riau, dan provinsi Sumatra Selatan). Forest fires in Indonesia have become a global problem that occurs every year, especially on the island of Sumatra. The identification of forest and land fires in this study is based on the number and distribution of hotspots, based on satellite image data from the Moderate Resolution Imaging Spectroradiometer (MODIS) in 2009-2018. Investigations on meteorological conditions are also based on global factors from Oceanic Nino Index (ONI) data, Dipole Mode Index (DMI) and based on the drought index from the Standardized Precipitation Index (SPI) data. The method used is a spatial and temporal analysis method. The purpose of this study was to determine the characteristics of hotspot distribution patterns on the island of Sumatra, both spatially and temporally. There are differences in the spatial and temporal characteristics of the hotspot distribution on the island of Sumatra, which is based on the characteristics of the topography, ENSO phase, as well as the wet and dry season periods. Orographic rain that occurred due to mountain topography in Aceh and the west coast of Sumatra resulted in reduced hotspots in the area. Meanwhile, El Nino increased the number of hotspots, while La Nina reduced the number of hotspots. Compared to IOD, ENSO is more influential on the occurrence of hotspot events on the island of Sumatra. The difference in the dry season period in northern, central and southern Sumatra also gives a difference in the time of the occurrence of maximum hotspots in Sumatra. The pattern of hotspot distribution in northern and central Sumatra peaked in February and June, while in the south in September. High hotspots (> 50 monthly events) with high concentrations occur on peatlands, which are commonly found in eastern Sumatra (province of North Sumatra, Riau, and South Sumatra).
EVALUATION OF THE CORDEX-SEA MODELS PERFORMANCE IN SIMULATING CHARACTERISTICS OF WET SEASON IN INDONESIA Rini Hidayati; Supari Supari; Alif Akbar Syafrianno; Akhmad Faqih
Jurnal Meteorologi dan Geofisika Vol. 24 No. 1 (2023)
Publisher : Pusat Penelitian dan Pengembangan BMKG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31172/jmg.v24i1.965

Abstract

Indonesia's climate is known to be challenging to adequately simulate by climate models because of the complexity of the weather system and sea-land distribution. Model evaluation is essential to measure confidence in the model results. This study evaluates the performance of the CORDEX-SEA model in simulating monthly rainfall patterns and the characteristics of seasonal rainfall, i.e., pattern, timing, length, and intensity, in Indonesia during 1986-2005. The performance of weighted (WMME) and unweighted ensemble methods are also calculated. Corrected CHIRPS data with similar seasonal patterns with point observation data is used as reference data to evaluate models. Percentage of the agreement of seasonal patterns between models and observation, FAR, and POD values were used to assess the model's ability to simulate seasonal patterns. WMME has the best seasonal patterns agreement with observation, 67% of all grids. The best model performance is shown by monsoonal patterns, with a POD value of 83% by WMME. Otherwise, all models could not describe an anti-monsoonal pattern, with a small POD (0-33%) and a high FAR (60-100%). In simulating the wet season on climatological, annual, and annual mean scales, both MMEs have similar performance and are better than individual models, with WMME performing best. However, on an annual scale, the yearly wet season produced by all models tends to approach its climatology value, making it less reliable in extreme years. Most models have higher daily and monthly rainfall than observation. In conclusion, the weighted ensemble method describes Indonesia's rainy season well, thus providing a reasonable basis for further research in climate projection analysis.
OVERSHOOTING TOP OF CONVECTIVE CLOUD IN EXTREME WEATHER EVENTS OVER JAVA REGION BASED ON VISUAL IDENTIFICATION OF HIMAWARI 8 IMAGERY Bony Septian Pandjaitan; Akhmad Faqih; Furqon Alfahmi; Perdinan .
Jurnal Meteorologi dan Geofisika Vol. 24 No. 1 (2023)
Publisher : Pusat Penelitian dan Pengembangan BMKG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31172/jmg.v24i1.967

Abstract

Overshooting top (OT) in convective clouds is an essential feature in extreme weather nowcasting performed by weather forecasters to represent the core location of the severe region of the convective cloud. In addition, we can estimate the location of extreme weather events by utilising OT climatology. Unfortunately, it cannot be realised in tropical Indonesia, especially on Java Island at present, because there still needs to be more research on the presence of OT in extreme weather events. This research aims to study the presence of OT in extreme weather events on Java Island using extreme weather reports and the Himawari 8 satellite data. We detect the presence or absence of OT patterns at the location of the extreme weather event with Visual identification by using a visible channel (0.64 μm) with a spatial resolution of 500 m and sandwich products. We found that about 87% of extreme weather occurred accompanied by the appearance of OT patterns from convective clouds. A parallax effect of Himawari 8 caused the detected OT location in the southwest direction of the actual location. Extreme weather events accompanied by the OT feature of convective clouds most often occur in the transitional period of the rainy to dry season (MAM) and the rainy season (DJF). Meanwhile, extreme weather events rarely occur during the dry season (JJA). Extreme weather events accompanied by OT often occur from midday to late afternoon. OT in this study has a diameter between 2-15 km during extreme weather events. A time lag between the appearance of OT and extreme weather events in Java Island gives us opportunities for approximating and nowcasting the extreme weather events.
UTILIZATION OF NEAR REAL-TIME NOAA-AVHRR SATELLITE OUTPUT FOR EL NIÑO INDUCED DROUGHT ANALYSIS IN INDONESIA (CASE STUDY: EL NIÑO 2015 INDUCED DROUGHT IN SOUTH SULAWESI) Amsari Mudzakir Setiawan; Yonny Koesmaryono; Akhmad Faqih; Dodo Gunawan
International Journal of Remote Sensing and Earth Sciences Vol. 13 No. 2 (2016)
Publisher : BRIN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2016.v13.a2450

Abstract

Drought is becoming one of the most important issues for government and policy makers. National food security highly concerned, especially when drought occurred in food production center areas. Climate variability, especially in South Sulawesi as one of the primary national rice production centers is influenced by global climate phenomena such as El Niño Southern Oscillation or ENSO. This phenomenon can lead to drought occurrences. Monitoring of drought potential occurrences in near real-time manner becomes a primary key element to anticipate the drought impact. This study was conducted to determine potential occurrences and the evolution of drought that occurred as a result of the 2015 El Niño event using the Vegetation Health Index (VHI) from the National Oceanic and Atmospheric Administration (NOAA) Advanced Very High Resolution Radiometer (AVHRR) satellite products. Composites analysis was performed using weekly Smoothed and Normalized Difference Vegetation Index (or smoothed NDVI) (SMN), Smoothed Brightness Temperature Index (SMT), Vegetation Condition Index (VCI), Temperature Condition Index (TCI), and Vegetation Health Index (VHI).  This data were obtained from The Center for Satellite Applications and Research (STAR) - Global Vegetation Health Products (NOAA) website during 35-year period (1981-2015). Lowest potential drought occurrences (highest VHI and VCI value) caused by 2015 El Niño is showed by composite analysis result. Strong El Niño induced drought over the study area indicated by decreasing VHI value started at week 21st. Spatial characteristic differences in drought occurrences observed, especially on the west coast and east coast of South Sulawesi during strong El Niño. Weekly evolution of potential drought due to the El Niño impact in 2015 indicated by lower VHI values (VHI < 40) concentrated on the east coast of South Sulawesi, and then spread to another region along with the El Nino stage. Â
Co-Authors Adyaksa Budi Raharja Agita Vivi Wijayanti Agus Buono Alexander Knohl Alif Akbar Syafrianno Alif Kurniawan Alimatul Rahim Amsari Mudzakir Setiawan Amsari Mudzakir Setiawan Amsari Mudzakir Setiawan Amsari Mudzakir Setiawan Ardhasena Sopaheluwakan Ashehad Ashween Ali Bony Septian Pandjaitan Christian Stiegler Daniel Murdiyarso Dodo Gunawan Dodo Gunawan Eddy Hermawan Ela Hasri Windari Elza Surmaini Erna Nur Aini Fildza Novadiwanti Fithriya Yulisiasih Rohmawati Furqon Alfahmi Furqon Alfahmi Gita Adhani Jadmiko, Syamsu Dwi Kartika, Qurrata A'yun Laode Nurdiansyah M. Mukhlis Mamenun Mamenun Misnawati, Misnawati Mulyono R. Prabowo Mulyono R. Prabowo Naziah Madani P. Perdinan Rahmat Hidayat Rini Hidayati Rizaldi Boer Santikayasa, I Putu Sanusi Sanusi Sitanggang, Imas S. Supari Supari Suria Tarigan Syamsu Dwi Jadmiko Tania June Ummu Ma'rufah Yonny Koesmaryono