Satria Indratmoko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Satria Indratmoko has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Fakhriaji Juliansyah
Department of Geography, Universitas Indonesia, Depok 16424, Indonesia
1 shared publication - Jarot Mulyo Semedi
Department of Geography, Universitas Indonesia, Depok 16424, Indonesia
1 shared publication - Josaphat Tetuko Sri Sumantyo
Center for Environmental Remote Sensing (CEReS), Chiba University, Chiba 263-8522, Japan
1 shared publication - Muhammad Dimyati
Department of Geography, Universitas Indonesia, Depok 16424, Indonesia
1 shared publication - Nurrokhmah Rizqihandari
Department of Geography, Faculty of Mathematics and Science, Universitas Indonesia, Depok 16424, Indonesia
1 shared publication - Pranda Mulya Putra Garniwa
Department of Geography, Universitas Indonesia, Depok 16424, Indonesia
1 shared publication
Latest Publications
- Open Access
Solar Irradiance Forecasting in Data-Sparse Tropical Regions Using a Novel Spatial Site-Adapted WRF–LSTM Hybrid Approach
Accurate solar irradiance forecasting in data-sparse tropical regions remains challenging due to complex terrain, rapid convective cloud formation, and limited ground-based observations. This study introduces a novel hybrid forecasting framework that integrates the Weather Research and Forecasting (WRF) model (10 km) with station-based Long Short-Term Memory (LSTM) bias correction, complemented by three innovative spatial site-adaptation strategies to produce spatially coherent short-term irradiance fields. The hybrid system leverages hourly Global Horizontal Irradiance (GHI) data from eight BMKG stations (2023) alongside GK2A satellite cloud information to dynamically correct WRF forecast biases, capturing nonlinear cloud–irradiance interactions that standard Numerical Weather Prediction (NWP) models fail to resolve. Results indicate that the hybrid WRF–LSTM system reduces 1–3-day root mean square error (RMSE) by 120–127 W/m2 and relative RMSE (rRMSE) by 26%, while lowering relative mean bias error (rMBE) from 31–36% (raw WRF) to 2.5–4.1%, with the largest improvements observed in regions exhibiting initially high WRF errors. Among the spatial adaptation methods, the average-based scheme minimizes RMSE but exhibits weak spatial coherence; the distance-weighted scheme achieves the strongest spatial consistency with regional reanalysis (R2 = 0.37) with minimal bias; and the elevation-based scheme ensures full-domain coverage with moderate skill. This study demonstrates that the integration of dynamical NWP modeling with LSTM-based bias correction and tailored spatial transfer strategies provides a robust, scalable approach for short-term solar irradiance forecasting and resource mapping in tropical environments. The proposed framework offers practical implications for PV power forecasting, grid management, and renewable energy planning in regions where observational data are sparse and the terrain is highly heterogeneous.
Open AccessSolar Irradiance Forecasting in Data-Sparse Tropical Regions Using a Novel Spatial Site-Adapted WRF–LSTM Hybrid Approach
Accurate solar irradiance forecasting in data-sparse tropical regions remains challenging due to complex terrain, rapid convective cloud formation, and limited ground-based observations. This study introduces a novel hybrid forecasting framework that integrates the Weather Research and Forecasting (WRF) model (10 km) with station-based Long Short-Term Memory (LSTM) bias correction, complemented by three innovative spatial site-adaptation strategies to produce spatially coherent short-term irradiance fields. The hybrid system leverages hourly Global Horizontal Irradiance (GHI) data from eight BMKG stations (2023) alongside GK2A satellite cloud information to dynamically correct WRF forecast biases, capturing nonlinear cloud–irradiance interactions that standard Numerical Weather Prediction (NWP) models fail to resolve. Results indicate that the hybrid WRF–LSTM system reduces 1–3-day root mean square error (RMSE) by 120–127 W/m2 and relative RMSE (rRMSE) by 26%, while lowering relative mean bias error (rMBE) from 31–36% (raw WRF) to 2.5–4.1%, with the largest improvements observed in regions exhibiting initially high WRF errors. Among the spatial adaptation methods, the average-based scheme minimizes RMSE but exhibits weak spatial coherence; the distance-weighted scheme achieves the strongest spatial consistency with regional reanalysis (R2 = 0.37) with minimal bias; and the elevation-based scheme ensures full-domain coverage with moderate skill. This study demonstrates that the integration of dynamical NWP modeling with LSTM-based bias correction and tailored spatial transfer strategies provides a robust, scalable approach for short-term solar irradiance forecasting and resource mapping in tropical environments. The proposed framework offers practical implications for PV power forecasting, grid management, and renewable energy planning in regions where observational data are sparse and the terrain is highly heterogeneous.
- Open Access
- 1 November 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 338 (1) , 012035
Burn Area Detection Using Landsat 8 OLI TIRS
Fires associated with land use conversion activities such as agricultural expansion, palm and pulp plantations, peat land alteration, and industrial deforestation are significant in Indonesia (Jerrod & Alex, 2015). Fires season in 2015 is one of the worst incident in Indonesia since 1997, it made Indonesia at the second position as an emitter country, at least 22 days in September 2015, and generated more than the daily average emission of U.S. economic activity. A study from the National Development Planning Agency (Bappenas) and Asian Development Bank (ADB) estimated that the amount of land affected by fires reaches 9.75 million hectares. It caused losses reached US$.4.861 or equivalent to IDR711 trillion or even more based on disruption of economic activities, transportation problems, and health problems. Head of Data Information and Public Relations of National Disaster Management Agency (BNPB), Sutopo Purwo Nugroho, said the economic impact of smog disasters occurring in several provinces in Indonesia in 2015 could exceed 20 trillion per province. The most widespread forest fire area occurred in South Sumatra Province. BNPB released that during 2015 in South Sumatera Province has 35.008 hotspots and the burnt area is 641.964 Ha. The most affected area is in Ogan Komering Ilir Regency. Landsat 8 OLI TIRS has a 30-meter spatial resolution for each band except TIRS band and panchromatic band (USGS, 2016). TIRS band has a 100-meter spatial resolution but are resampled to 30-meter that can be used to identify burned scars area. By using SWIR bands (TM bands 5 and 7 in Landsat 5 and 7 systems) as a NBR (Normalized burn ratio) composite, can be used to detecting and mapping burnt area. TIRS algorithm which was used to detect fire will be seen red and SWIR which was used to detect water stress in vegetation and burned vegetation will be seen green, both of them will become darker when burn happened. This method modifying dNBR (pre-NBR – post-NBR) composite, which only can be used in oil palm plantations area that has same commodities, so can be used in various type of landuse especially the area that has plantation adjoin with forest area.
- 1 November 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 338 (1) , 012035
Open AccessBurn Area Detection Using Landsat 8 OLI TIRS
Fires associated with land use conversion activities such as agricultural expansion, palm and pulp plantations, peat land alteration, and industrial deforestation are significant in Indonesia (Jerrod & Alex, 2015). Fires season in 2015 is one of the worst incident in Indonesia since 1997, it made Indonesia at the second position as an emitter country, at least 22 days in September 2015, and generated more than the daily average emission of U.S. economic activity. A study from the National Development Planning Agency (Bappenas) and Asian Development Bank (ADB) estimated that the amount of land affected by fires reaches 9.75 million hectares. It caused losses reached US$.4.861 or equivalent to IDR711 trillion or even more based on disruption of economic activities, transportation problems, and health problems. Head of Data Information and Public Relations of National Disaster Management Agency (BNPB), Sutopo Purwo Nugroho, said the economic impact of smog disasters occurring in several provinces in Indonesia in 2015 could exceed 20 trillion per province. The most widespread forest fire area occurred in South Sumatra Province. BNPB released that during 2015 in South Sumatera Province has 35.008 hotspots and the burnt area is 641.964 Ha. The most affected area is in Ogan Komering Ilir Regency. Landsat 8 OLI TIRS has a 30-meter spatial resolution for each band except TIRS band and panchromatic band (USGS, 2016). TIRS band has a 100-meter spatial resolution but are resampled to 30-meter that can be used to identify burned scars area. By using SWIR bands (TM bands 5 and 7 in Landsat 5 and 7 systems) as a NBR (Normalized burn ratio) composite, can be used to detecting and mapping burnt area. TIRS algorithm which was used to detect fire will be seen red and SWIR which was used to detect water stress in vegetation and burned vegetation will be seen green, both of them will become darker when burn happened. This method modifying dNBR (pre-NBR – post-NBR) composite, which only can be used in oil palm plantations area that has same commodities, so can be used in various type of landuse especially the area that has plantation adjoin with forest area.