This study explores the forecasting accuracy of SARIMAX, LSTM, and XGBoost models in predicting solar PV output using one-year data from three solar PV installations in the Philippines. The research aims to compare the performance of these models with their hybrid counterparts and investigate their performance. The study utilizes the adjusted shortwave radiation (SWR) product in the Advanced Himawari Imager 8 (AHI-8), as a proxy for in situ solar irradiance, and weather parameters, to improve the accuracy of the forecasting models. The results show that SARIMAX outperforms LSTM, XGBoost, and their combinations for Plants 1 and 2, while XGBoost performs best for Plant 3. Contrary to previous studies, the hybrid models did not provide more accurate forecasts than the individual methods. The performance of the models varied depending on the forecasted month and installation site. Using adjusted SWR and other weather parameters, as inputs in forecasting solar PV output, adds novelty to this research. Future research should consider comparing the accuracy of using adjusted SWR alone and combined with other weather parameters. This study contributes to solar PV output forecasting by utilizing adjusted satellite-derived solar radiation, and combining SARIMAX, LSTM, and XGBoost models, including their hybrid counterparts, in a single and comprehensive analysis.

This study investigated the drivers of degradation in Southeast Asian mangroves through multi-source remote sensing data products. The degradation drivers that affect approximately half of this area are unidentified; therefore, naturogenic and anthropogenic impacts on these mangroves were studied. Various global land cover (GLC) products were harmonized and examined to identify major anthropogenic changes affecting mangrove habitats. To investigate the naturogenic factors, the impact of the water balance was evaluated using the Normalized Difference Vegetation Index (NDVI), and evapotranspiration and precipitation data. Vegetation indices’ response in deforested mangrove regions depends significantly on the type of drivers. A trend analysis and break point detection of percentage of tree cover (PTC), percentage of non-tree vegetation (PNTV), and percentage of non-vegetation (PNV) datasets can aid in measuring, estimating, and tracing the drivers of change. The assimilation of GLC products suggests that agriculture and fisheries are the predominant drivers of mangrove degradation. The relationship between water balance and degradation shows that naturogenic drivers have a wider impact than anthropogenic drivers, and degradation in particular regions is likely to be a result of the accumulation of various drivers. In large-scale studies, remote sensing data products could be integrated as a remarkably powerful instrument in assisting evidence-based policy making.

This study proposes a modified gaps filling method, expanding the column mean imputation method and evaluated using randomly generated missing values comprising 5%, 10%, 15%, and 20% of the original data on power output. The XGBoost algorithm was implemented as a forecasting model using the original and processed datasets and two sources of solar radiation data, namely, Shortwave Radiation (SWR) from Advanced Himawari Imager 8 (AHI-8) and Surface Solar Radiation Downward (SSRD) from ERA5 global reanalysis data. The accuracy of the two sets of forecasted power output was evaluated using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Results show that by applying the proposed gap filling method and using SWR in forecasting solar photovoltaic (PV) output, the improvement in the RMSE and MAE values range from 12.52% to 24.30% and from 21.10% to 31.31%, respectively. Meanwhile, using SSRD, the improvement in the RMSE values range from 14.01% to 28.54% and MAE values from 22.39% to 35.53%. To further evaluate the accuracy of the proposed gap-filling method, the proposed method could be validated using different datasets and other forecasting methods. Future studies could also consider applying the said method to datasets with data gaps higher than 20%.

Forecasting models are often constrained by data availability, and in forecasting solar photovoltaic (PV) output, the literature suggests that solar irradiance contributes the most to solar PV output. The objective of this study is to identify which between the satellite-based and reanalysis solar irradiance data, namely, short wave radiation (SWR) and surface solar radiation downward (SSRD), respectively, is a better alternative to in situ solar irradiance in forecasting solar PV output should the latter become unavailable. Nine seasonal autoregressive integrated moving average with exogenous variables (SARIMAX) models were presented in this study to assess the forecasting performance of each solar irradiance data together with weather parameters. Using only historical data to forecast solar PV output, three seasonal autoregressive integrated moving average (SARIMA) models were run to forecast solar PV output and to compare and validate the efficacy of the SARIMAX models. The analysis was divided into seasons as defined by the Philippine Atmospheric, Geophysical and Astronomical Services Administration: hot dry, rainy, and cool dry. Results show that the use of SSRD is a better alternative than SWR when forecasting solar PV output for the hot dry season and cool dry season. For the hot dry season, SSRD has an root mean square error (RMSE) value of 0.411 kW while SWR has 0.416 kW. For the cool dry season, SSRD has an RMSE value of 0.457 kW while SWR has 0.471 kW. Meanwhile, SWR outperforms SSRD when forecasting solar PV output during the rainy season, with RMSE values at 0.375 and 0.401 kW, respectively.

The intensity of solar radiation (SR) is one of the most important required inputs for the estimation of photovoltaic (PV) power station output. Meanwhile, the efficiency of solar PV systems is affected by meteorological factors such as temperature, dust, precipitation, and snow. Meteorological data from satellites provide a viable way for estimating PV potential due to its advantage in spatial coverage and temporal resolution. This paper presents a new approach to adjust SR data from satellites based on the cloud optical thickness (CLOT) before evaluating the solar PV power (P_PV) potential, with the effective efficiency of solar cells computed based on temperature, dust, precipitation, and snow. The objective of this study is to evaluate the over-all spatiotemporal solar PV potential in the Asia Pacific region which will holistically include limiting meteorological factors and identify which factor contributes most significantly to the decrease in solar PV potential in selected cities in the region. First, SR and CLOT data from Advanced Himawari Imager 8 and a SKYNET station were processed to derive the correction factor for solar radiation data. Second, satellite data for temperature (MOD11), precipitation (global satellite mapping of precipitation), dust (MOD04), and snow cover (MOD10) were processed to derive the effective solar PV efficiency. Finally, maps showing the seasonal PV power potential over the Asia Pacific region were generated, with selected cities zoomed in for detailed analysis using mean monthly values from March 2016 to February 2017. The results showed that the maximum theoretical P_PV in the region was estimated to be 1.9 GW per 17.5 km² effective pixel area. Moreover, P_PV decreased by maximum values of 180 MW, 550 MW, and 225 MW due to temperature, dust, and snow, respectively. For Beijing, Tokyo, and Jakarta, the major contributor to the decrease in P_PV is dust, while Khabarovsk is consistently affected by snow effects. Initial validation of the model shows over- and underestimation of solar PV output compared to the actual values by as high as 30%. However, very high values of coefficient of determination (>0.90) show promising results of the model. The contribution of this study is two-fold: regional-scale assessment of P_PV potential and investigation of the collective effect and individual contributions of dust, temperature, and snow to the decrease in P_PV potential.