Richard Mahendra Putra - Academia.edu (original) (raw)

Teaching Documents by Richard Mahendra Putra

Hal yang biasa dilupakan oleh kita ketika memanfaatkan data satelit adalah kesalahan paralaks sat... more Hal yang biasa dilupakan oleh kita ketika memanfaatkan data satelit adalah kesalahan paralaks satelit. Ketika awan berada jauh dari posisi satelit, maka awan akan diposisikan pada suatu permukaan yang bergeser dari kondisi aslinya. Nilai dari pergeseran ini akan lebih besar ketika berada di belahan bumi yang jauh dari equator. Koreksi paralaks ini sangatlah penting terutama ketika menganalisis lokasi awan cumulonimbus yang sebenarnya.

SI = 0.40 KI = 37.00 LI = 0.6 SWEAT = 250.4 TT = 42.50 CAPE = 76.79 J/kg CIN = -31.79 (Source ; W... more SI = 0.40 KI = 37.00 LI = 0.6 SWEAT = 250.4 TT = 42.50 CAPE = 76.79 J/kg CIN = -31.79 (Source ; Wyoming University) @Japof_Meteorology Analisa Hodograph daerah PKP PPBB 65008 96237 90/15 25004 18007 13512 9067/ 13509 09506 9106/ 09011 12035 931// 08541 949// 09538 95345 08554 08536 06010 @Japof_Meteorology

Data yang mempresentasikan dunia nyata (real world) dapat disimpan, dimanipulasi, diproses, dan d... more Data yang mempresentasikan dunia nyata (real world) dapat disimpan, dimanipulasi, diproses, dan dipresentasikan dalam bentuk yang lebih sederhana dengan layer-layer tematik yang direlasikan dengan lokasi-lokasi geografi di permukaan bumi, dan hasilnya dapat dipergunakan untuk pemecahan banyak masalah-masalah dunia nyata seperti dalam perencanaan , pelaksanaan, pemantauan, evaluasi, pemodelan dan pengambilan keputusan menyangkut data kebumian.

Nah seperti yang telah dibahas sebelumnya, data yang akan kita gunakan adalah data FNL. Sebenarny... more Nah seperti yang telah dibahas sebelumnya, data yang akan kita gunakan adalah data FNL. Sebenarnya proses running dan lain sebagainya adalah sama. Namun hingga saat ini kami belum tahu dimana alamat yang menyediakan data GFS. Jadi tidak apa-apa ya kita belajar analisis dulu.. :D Oke, pertama kita masuk ke dalam situs yang menyediakan data FNL, yaitu :

2022 International Conference on Science and Technology (ICOSTECH)

The high sun radiation levels in Indonesia result in a convective process that can influence a ve... more The high sun radiation levels in Indonesia result in a convective process that can influence a very fast life cycle of cloud growth. It causes difficulty in weather prediction. WRF-ARW model is an advanced model of mesoscale numerical weather system which can provide images of atmospheric conditions in a region. The most important thing in this model is the test of parameterization. One of them is cumulus parameterization that is very important in the process of cloud formation. In this study, the cumulus parameterization was tested in Kupang and Surabaya Regions. The test was performed on the cumulus schemes of Kain-Fritsch (KF) and Betts Miller Janjic (BMJ) by using Final Analysis (FNL) as model input data for making simulation of Upper Air Condition in Surabaya and Kupang Regions. The result of study showed that different configuration for parameterization scheme depended on what kind of data that we wanted to simulate and where the place was. For all of the parameters compared, ...

IOP Conference Series: Earth and Environmental Science, 2021

Increase in frequency and strength of cumulonimbus is one of the impacts of climate change. The p... more Increase in frequency and strength of cumulonimbus is one of the impacts of climate change. The presence of cumulonimbus usuallyy causes extreme weather. Cumulonimbus can produce heavy rainfalls, tornadoes, turbulences, and other extreme weather events. Upper air conditions have a great effect on the process of cloud growth. Radiosonde observations can be used to predict the presence of cumulonimbus in the short-term period of weather forecast. This study aimed to predict the occurrence of cumulonimbus using radiosonde data based on the machine learning approach. In this study, indices data from upper-air observation were used. The model prediction of radiosonde data was trained using machine learning to predict the presence of cumulonimbus. Based on data processing results, the prediction of cumulonimbus events using radiosonde indices data is good enough when implemented in new test data. The influence of the Convective Available Potential Energy (CAPE) index in the predictor inde...

2018 3rd International Seminar on Sensors, Instrumentation, Measurement and Metrology (ISSIMM), 2018

Journal of Physics: Conference Series, 2020

It was recorded that in August 2019 the case of acute respiratory infection in Indonesia had doub... more It was recorded that in August 2019 the case of acute respiratory infection in Indonesia had doubled compared to the previous months. This is in line with the increasing levels of PM10 and PM2.5 in several regions in Indonesia. In the end the public is increasingly aware of the importance of air quality information. Prediction of air quality will greatly help the public to anticipate the dangers of declining air quality. The use of Artificial Neural Network can be a solution in making daily air quality forecasts whose parameters are not linear. This research shows that utilization of historical data parameters of temperature, humidity, air pressure, rainfall, sun exposure and wind speed as well as BMKG’s PM10 and PM2.5 data is able to produce forecasting modeling for PM2.5 and PM10 concentrations in the Kemayoran area, Jakarta by utilizing Artificial Neural Network Modeling. The result is success to make prediction of PM2.5 and PM10 and it will be better if more historical data appl...

INTERNATIONAL CONFERENCE ON SCIENCE AND APPLIED SCIENCE (ICSAS) 2019, 2019

Volcanic ash is a significant phenomenon towards aviation safety and capacity of influencing clim... more Volcanic ash is a significant phenomenon towards aviation safety and capacity of influencing climate change. Therefore, accurate information of the volcanic ash spatial distribution in the atmosphere possessed a fundamental role in the community. Polar type satellites such as Terra / Aqua equipped with MODIS sensors are capable of providing vivid imagery of the volcanic ash spatial distribution. However, the deficiency of this satellite is unable to perform optimal imagery for real-time monitoring due to its limitation require to be located above the volcanic ash site. Therefore, a geostationary satellite is a feasible solution to solve this issue hence its capability to observe specified fixed location continuously. Despite its capability, this type of satellite also performs designated weaknesses hence non-absolute perpendicularity observation angles on certain conditions towards the observed objects from the satellite fixed position. The purpose of this study is to create an automatic detection system using Himawari-8 satellite observations data by applying Artificial Neural Network (ANN) with training datasets and utilizing Terra / Aqua polar type satellite with MODIS sensors as validator. The input variation based on previous research references were using three bands, all bands, and four variations of satellite bands. The result of the study justifies the models established using all bands and four variation bands can produce good performances in training data, although less consistent if applied towards other cases. While the singlepixel model with three-band input well suited over Mt. Merapi volcanic eruption event on June 1st, 2018 with 93.71% accuracy

IOP Conference Series: Earth and Environmental Science, 2019

Satellite-based rainfall estimation is evolving rapidly. Most studies use data, which is spatiall... more Satellite-based rainfall estimation is evolving rapidly. Most studies use data, which is spatially fine, but poorly regarding time. On the other hand, availability of verification data is also quite rare. This study used Hillman Form B report that was corrected by ME-48 from Malang Climatological Station. 2009-2016 IR1 satellite data were used in hourly temporal resolution (only less than 3% data missing). Four estimation methods were compared: Auto Estimator, CST, mCST, and Quantile Analysis Equation. Data processing was carried out using Python and R statistic as a quality control. The analysis was done by creating a graph that combines False Alarm and Miss Information for each rainfall intensity. Binary transformation was done for enabling information to be plotted. All rainfall estimation methods have a high false alarm (more than 74% at 1 mm) but quite low miss (less than 0.03%). By taking into account its error pattern, satellite data can be used in rainfall observation. The Q...

Informasi tentang impact based forecast (IBF) biasanya difokuskan pada kejadian yang berada di pe... more Informasi tentang impact based forecast (IBF) biasanya difokuskan pada kejadian yang berada di permukaan
saja, seperti dampak banjir bandang, bencana di Daerah Aliran Sungai, dan lain sebagainya. Informasi cuaca
berbasis dampak juga diperlukan di dunia penerbangan untuk mengantisipasi kecelakaan pesawat. Belum
pernah ada kajian terkait IBF) yang digunakan untuk dunia penerbangan. Pada penelitian ini, difokuskan
dalam membuat produk prakiraan cuaca berbasis dampak untuk dunia penerbangan dengan menggunakan
data-data yang dihasilkan dari System of Indonesian Aviation Meteorology (SIAM). Produk dari cuaca
berbasis dampak tetap pada keputusan forecaster dalam menentukan potensi dampak yang dihasilkan serta
peluang kejadiannya. Dampak yang dijelaskan pada penelitian ini adalah dampak yang dirasakan oleh pesawat
saat melewati area yang diprakirakan terjadi fenomena turbulensi akibat awan konvektif. Dalam penelitian ini
digunakan hasil keluaran produk yang sudah ada di SIAM, yaitu Cumulonimbus Cloud Prediction kemudian
dikombinasikan dengan hasil prediksi awan cumulonimbus berdasarkan data labilitas udara ECMWF yang
dibuat menggunakan Machine Learning. Berdasarkan hasil penelitian, potensi pertumbuhan awan
cumulonimbus dengan sistem yang sudah ada di SIAM dan hasil keluaran Machine Learning dapat digunakan
sebagai acuan forecaster dalam membuat prakiraan cuaca berbasis dampak untuk sektor penerbangan.
Berdasarkan hasil verifikasi dengan menggunakan data sebaran awan cumulonimbus dari satelit Himawari-8
selama 12 jam, produk Prakiraan Cuaca Berbasis Dampak untuk sektor penerbangan ini memiliki akurasi 90%

Salah satu bahaya terbesar pada dunia penerbangan adalah debu vulkanik. Selain berdampak menyebab... more Salah satu bahaya terbesar pada dunia penerbangan adalah debu vulkanik. Selain berdampak
menyebabkan kecelakaan, sebaran debu vulkanik juga dapat mempengaruhi perubahan iklim.
Informasi distribusi debu vulkanik sangat penting untuk meningkatkan keselamatan kegiatan
penerbangan. Saat ini, informasi sebaran abu vulkanik dilakukan dengan interpretasi citra
satelit yang menggunakan metode RBG Composite. Tujuan dari penelitian ini adalah untuk
membuat produk deteksi otomatis distribusi debu vulkanik menggunakan satelit Himawari-8
dengan menggunakan model artificial neural network (ANN). Model ANN dilakukan pelatihan
pada studi kasus letusan Gunung Sinabung pada 19 Februari 2018 dan diuji dalam studi kasus
lainnya, yaitu letusan Gunung Merapi 11 Mei 2018, Gunung Rinjani 3 November 2015, dan
Gunung Agung 2 Juli 2018. Berdasarkan hasil tersebut, distribusi debu vulkanik memiliki pola
yang mirip dengan interpretasi produk RGB Composite produk sebaran debu vulkanik yang
digunakan oleh BMKG.

Sejak awal tahun 2020, wilayah Jakarta berulang kali dilanda banjir yang diakibatkan oleh hujan e... more Sejak awal tahun 2020, wilayah Jakarta berulang kali dilanda banjir yang diakibatkan
oleh hujan ekstrem. Teknologi prakiraan cuaca berbasis Numerical Weather Prediction (NWP)
sudah populer saat ini untuk mengetahui kondisi cuaca di masa depan. Namun karena kondisi
lokal dan karakteristik wilayah Indonesia yang rumit, terkadang output prakiraan cuaca
berdasarkan NWP kurang tepat. Penelitian ini akan mencoba untuk membuat sebuah produk
prakiraan hujan Probabilistik menggunakan beberapa waktu inisial yang berbeda (time-lagged
ensemble). Studi kasus yang dipilih dalam penelitian ini adalah kejadian hujan esktrem di
Jakarta pada tanggal 31 Desember 2019, 24 Januari 2020, dan 24 Februari 2020. Terdapat 4
output produk yang akan diuji dalam penelitian ini, yaitu probabilistik model A, model B,
model C, dan model D. Berdasarkan hasil penelitian, kejadian hujan ekstrem yang terjadi di
wilayah Jakarta dapat terdeteksi sinyal kejadiannya berdasarkan seluruh model sejak 3 hari
sebelum kejadian. Hasil output dari produk probabilistik model C dan model D menunjukkan
hasil yang underestimate untuk intensitas hujan yang terjadi, namun dapat digunakan sebagai
sinyal kejadian fenomena ekstrem tersebut. Sedangkan area yang berpotensi terjadi hujan
ekstrem tidak dapat diketahui lokasinya pada output model A dan model B akibat dari nilai
probabilitas yang tinggi di seluruh area

For the convective cloud situation, there is an assumption that lower cloud top temperature is as... more For the convective cloud situation, there is an assumption that lower cloud top temperature is associated with heavier rainfall. Research of relationship between rainfall and satellite data can be done through the analysis of cloud top brightness temperature which showed on 10.4µm channel furthermore can be utilized to estimate the amount of precipitation in the future. This paper aims to determine and analyze the relationship between the average of cloud top brightness temperature from Himawari-8 satellite IR1 data with the rainfall per hour data were observed on February 2016 at Perak I Surabaya Meteorological Station. The results of the analysis can be used to determine the distribution and the character of cloud top brightness temperature values during rain events at the sites. Analysis of the relationship is done by using warmer or colder average cloud top brightness temperature than-50 o C treshold and divide it into several groups events. The result show that from 154 rainfall events data there are 60 (38.96%) events of the total rain events are accompanied by colder average cloud top brightness temperature than-50°C, and there are 94 (61.04%) events of the total rain events are accompanied by the warmer average cloud top brightness temperature than-50°C. In general can be said that with the warmer average cloud top brightness temperature than-50 o C, rain in the region of Perak I Surabaya Meteorological Station still can occur. The condition occurs in two circumstance, those are when in the same period time of rain there are colder or warmer cloud top brightness temperature than-50°C. The result of the the analysis for precipitation cloud characteristic shows that for the rain event which not accompanied by colder cloud top temperature than-50 o C can occurs becuase an parallax error of cloud observation angle. This parallax error causes the cloud with top cloud temperature value colder than-50 o C not exactly detected above the interest area.

Prakiraan cuaca sangat penting untuk mendukung segala kegiatanaktivitasmasyarakat. Unt... more Prakiraan cuaca sangat penting untuk mendukung segala kegiatanaktivitasmasyarakat. Untuk menghasilkan prakiraan cuaca yang akurat dibutuhkan pengetahuan dan pengalaman dari prakirawan cuaca yang didukung dengan teknologi pemodelan cuaca. Pada penelitian ini, dilakukansebuah pemodelan curahhujan menggunakan artificial neural network(ANN) di Stasiun Meteorologi Kemayoran. Pada proses pembuatan model ANN, dibutuhkan pelatihan data menggunakan kondisi cuaca di masa lalu. Data yang digunakan untuk pelatihan dalam membuat model ANN adalah data cuaca harianperiode Januari 2011 s.d. Desember 2019yang selanjutnya diuji dengan menggunakan studi kasus selamaperiodeJanuari s.d. Agustus 2020. Variasi model dibuat berdasarkan jenis inputdan jumlah hidden layeruntuk mengetahui perbedaan penggunaan data prediktor yang digunakan. Kemudian model ANN dibuat dengan menggunakan pendekatan 3–lapisanyang terdiri dari lapisaninput, lapisan tersembunyi, dan lapisan output.Selanjutnya perbandingan model tersebut diuji menggunakan nilai koefisien korelasi (R) dan rata–rata kesalahan absolut (MAE) untuk mengetahui model yang terbaik. Berdasarkan hasil penelitian, prediksi hujan menggunakan data parameter inputkondisi cuaca harianberupa suhu udara, kelembaban udara, dan durasi penyinaran mataharimemiliki nilai koefisien korelasi (R) sebesar 0.4–0.5dan rata–rata kesalahan absolut (MAE) sebesar 9.7–9.8mm. Sedangkan jika model dibuat dengan parameter inputhujan di hari –hari sebelumnya, nilai koefisien korelasi (R) hanya 0.1–0.3dengan nilai rata–rata kesalahan absolut (MAE)sebesar 11.3 –12.3 mm.Kondisi tersebut menunjukkan bahwa prediktor yang lebih baik digunakan dalam memprediksi hujan harian berdasarkanartificial neural networkadalah denganmenggunakan parameter inputkondisi cuaca permukaan.

IOP Publishing, 2021

GAW Bariri, 2020

Abstrak. Prakiraan cuaca sangat penting untuk mendukung segala kegiatan aktivitas masyarakat. Unt... more Abstrak. Prakiraan cuaca sangat penting untuk mendukung segala kegiatan aktivitas masyarakat. Untuk menghasilkan prakiraan cuaca yang akurat dibutuhkan pengetahuan dan pengalaman dari prakirawan cuaca yang didukung dengan teknologi pemodelan cuaca. Pada penelitian ini, dilakukan sebuah pemodelan curah hujan menggunakan artificial neural network (ANN) di Stasiun Meteorologi Kemayoran. Pada proses pembuatan model ANN, dibutuhkan pelatihan data menggunakan kondisi cuaca di masa lalu. Data yang digunakan untuk pelatihan dalam membuat model ANN adalah data cuaca harian periode Januari 2011 s.d. Desember 2019 yang selanjutnya diuji dengan menggunakan studi kasus selama periode Januari s.d. Agustus 2020. Variasi model dibuat berdasarkan jenis input dan jumlah hidden layer untuk mengetahui perbedaan penggunaan data prediktor yang digunakan. Kemudian model ANN dibuat dengan menggunakan pendekatan 3-lapisan yang terdiri dari lapisan input, lapisan tersembunyi, dan lapisan output. Selanjutnya perbandingan model tersebut diuji menggunakan nilai koefisien korelasi (R) dan rata-rata kesalahan absolut (MAE) untuk mengetahui model yang terbaik. Berdasarkan hasil penelitian, prediksi hujan menggunakan data parameter input kondisi cuaca harian berupa suhu udara, kelembaban udara, dan durasi penyinaran matahari memiliki nilai koefisien korelasi (R) sebesar 0.4-0.5 dan rata-rata kesalahan absolut (MAE) sebesar 9.7-9.8 mm. Sedangkan jika model dibuat dengan parameter input hujan di hari-hari sebelumnya, nilai koefisien korelasi (R) hanya 0.1-0.3 dengan nilai rata-rata kesalahan absolut (MAE) sebesar 11.3-12.3 mm. Kondisi tersebut menunjukkan bahwa prediktor yang lebih baik digunakan dalam memprediksi hujan harian berdasarkan artificial neural network adalah dengan menggunakan parameter input kondisi cuaca permukaan.

Volcanic ash produced by eruptions has been significantly dangerous towards aviation. The necessi... more Volcanic ash produced by eruptions has been significantly dangerous towards aviation. The necessity of volcanic ash early warning system distribution is crucial to reduce casualties on aircraft accident. In this paper, some techniques of volcanic ash detection were compared to find the proper algorithm to visualize the volcanic ash distribution. The multispectral image was acquired from the geostationary satellite (Himawari-8 satellite) in specific time observation. The reference data were collected from the MODIS sensor in the Aqua satellite to monitor the volcanic ash distribution at the same time and place. The first method is to generate the value of brightness temperature differences (BTD) at 11 µm and 12 µm wavelengths. The second method is conducted by inserting 3.9 µm information from the product of three-band volcanic ash known as (TVAP). The third method is a combination of the first and second method while the last method utilizes RGB composite color combination from several bands of Himawari-8. The reference data collected by MODIS Observation at 06.00 UTC. The BTD technique unable to detect low-intensity volcanic ash, while combining it with the TVAP method can increase the standard method performance. Based on expert judgment, BTD technique has a good performance for thick volcanic ash although unable to detect thin volcanic ash distribution. Three-band Volcanic Ash Product (TVAP) method could detect thick and thin volcanic ash. The combination of BTD and TVAP method has an excellent result to observe volcanic ash distribution, but the result tends to overestimate like TVAP distribution. RGB Methods from JMA Configuration have the same pattern and distribution of volcanic ash as MODIS observation. Based on the study results, BTD, TVAP, and RGB composite methods can produce good results compared to MODIS imagery for monitoring the volcanic ash distribution.

It was recorded that in August 2019 the case of acute respiratory infection in Indonesia had doub... more It was recorded that in August 2019 the case of acute respiratory infection in Indonesia had doubled compared to the previous months. This is in line with the increasing levels of PM10 and PM2.5 in several regions in Indonesia. In the end the public is increasingly aware of the importance of air quality information. Prediction of air quality will greatly help the public to anticipate the dangers of declining air quality. The use of Artificial Neural Network can be a solution in making daily air quality forecasts whose parameters are not linear. This research shows that utilization of historical data parameters of temperature, humidity, air pressure, rainfall, sun exposure and wind speed as well as BMKG's PM10 and PM2.5 data is able to produce forecasting modeling for PM2.5 and PM10 concentrations in the Kemayoran area, Jakarta by utilizing Artificial Neural Network Modeling. The result is success to make prediction of PM2.5 and PM10 and it will be better if more historical data applied.

Weather conditions are a significant factor for various sectors such as transportation safety, de... more Weather conditions are a significant factor for various sectors such as transportation safety, development, health, etc. Therefore, high development is needed in forecasting future weather conditions. Many ways are used to predict weather conditions. Along with the development of technology now, weather prediction can be made using Artificial Intelligence (AI) technology or artificial intelligence so that the results obtained are more optimal. In this study, the artificial neural network used has a feedforward neural network algorithm using training data consisting of temperature, air pressure, air humidity, wind speed, hourly wind speed at the Juanda Meteorological Station in Surabaya in Januari 2019 with the target is intensity of rainfall. Furthermore, the data was released in the period of 1 January 2019 to 31 Januari 2019. Based on the analysis results, the Artificial Neural Network model has a fairly good performance in predicting an increase in rainfall in Surabaya. The best model is considered by a model with architecture 7-60-1 with an estimate correlation is 0.87, with an error value of-0.03. With this model, it is expected to become one of the forecaster considerations in making special weather forecasts at intervals every hour.

BULETIN METEO NGURAH RAI, 2020

ABSTRAK Benua maritim Indonesia memiliki karakteristik cuaca dan kondisi iklim yang unik. Di kawa... more ABSTRAK Benua maritim Indonesia memiliki karakteristik cuaca dan kondisi iklim yang unik. Di kawasan ini terdapat beberapa faktor global, regional dan lokal yang menyebabkan kondisi cuaca dan iklim. Untuk skala global faktor iklim yang mempengaruhi benua maritim Indonesia adalah El Nino Southern Oscillation (ENSO), Indian Ocean Dipole (IOD) dan Madden Julian Oscillation (MJO). Kombinasi dari ketiga faktor global tersebut akan mempengaruhi kondisi cuaca dan Iklim di Indonesia. Dalam penelitian ini dibuat model Machine Learning menggunakan data yang dilatih selama tahun 2000 sampai 2016 untuk mengetahui intensitas curah hujan bulanan berdasarkan kombinasi ENSO, IOD, dan MJO. Beberapa model terdiri dari semua faktor untuk prediktor, model lain hanya terdiri dari beberapa faktor kombinasi saja, seperti kombinasi MJO dan IOD, kombinasi SOI dan MJO, serta kombinasi IOD dan SOI. Berdasarkan hasil tersebut, nilai korelasi model terbaik di setiap pulau berada pada rentang 0,56-0,86 dengan hasil terbaik ada di Pulau Sumatera. Faktor global yang mempengaruhi intensitas hujan bulanan tergantung pada lokasi penelitian. Nilai Mean Absolut Error (MAE) berkisar antara 20.03-97.20 mm/bulan. Nilai MAE menunjukkan model terbaik adalah saat prediktor menggunakan semua faktor untuk menghitung intensitas curah hujan di Sumatera dan Pulau Jawa. Sedangkan untuk Pulau Kalimantan, model terbaik ditampilkan ketika prediktor hanya terdiri dari SOI dan MJO. Untuk Sulawesi, hasil model menunjukkan bahwa IOD dan MJO merupakan prediktor terbaik untuk intensitas curah hujan berbasis Machine Learning. ABSTRACT The Indonesian maritime continent has unique weather characteristics and climatic conditions. In this region there are several global, regional and local factors that cause weather and climatic conditions. For the global scale, the climate factors that affect the maritime continent of Indonesia are the El Nino Southern Oscillation (ENSO), the Indian Ocean Dipole (IOD) and the Madden Julian Oscillation (MJO). The combination of these global factors will influence weather and climate conditions in Indonesia. In this study, Machine Learning model was created using data trained from 2000 to 2016 to determine the intensity of monthly rainfall based on a combination of ENSO, IOD, and MJO. Some models consist of all factors for predictors, other models only consist of a few combination factors, such as the combination of MJO and IOD, the combination of SOI and MJO, and the combination of IOD and SOI. Based on these results, the best model correlation values in each island are in the range 0.56-0.86 with the best results in Sumatera Island. Global factors affecting monthly rainfall intensity depend on the research location. Mean Absolute Error (MAE) values between from 20.03-97.20 mm / month. MAE value shows that the best model is when the predictor uses all factors to calculate the intensity of rainfall in Sumatra and Java. Whereas for Kalimantan

Buletin Meteorologi Klimatologi dan Geofisika, 2019

AIP Conference Proceedings 2202, 020112 (2019), 2019

Volcanic ash is a significant phenomenon towards aviation safety and capacity of influencing clim... more Volcanic ash is a significant phenomenon towards aviation safety and capacity of influencing climate change.
Therefore, accurate information of the volcanic ash spatial distribution in the atmosphere possessed a fundamental role in
the community. Polar type satellites such as Terra / Aqua equipped with MODIS sensors are capable of providing vivid
imagery of the volcanic ash spatial distribution. However, the deficiency of this satellite is unable to perform optimal
imagery for real-time monitoring due to its limitation require to be located above the volcanic ash site. Therefore, a
geostationary satellite is a feasible solution to solve this issue hence its capability to observe specified fixed location
continuously. Despite its capability, this type of satellite also performs designated weaknesses hence non-absolute
perpendicularity observation angles on certain conditions towards the observed objects from the satellite fixed position.
The purpose of this study is to create an automatic detection system using Himawari-8 satellite observations data by
applying Artificial Neural Network (ANN) with training datasets and utilizing Terra / Aqua polar type satellite with MODIS
sensors as validator. The input variation based on previous research references were using three bands, all bands, and four
variations of satellite bands. The result of the study justifies the models established using all bands and four variation bands
can produce good performances in training data, although less consistent if applied towards other cases. While the singlepixel model with three-band input well suited over Mt. Merapi volcanic eruption event on June 1st, 2018 with 93.71%
accuracy