Harmful algal bloom (HAB) events have alarmed authorities of human health that have caused severe illness and fatalities, death of marine organisms, and massive fish killings. This work aimed to perform the long short-term memory (LSTM) method and convolution neural network (CNN) method to predict the HAB events in the West Coast of Sabah. The results showed that this method could be used to predict satellite time series data in which previous studies only used vector data. This paper also could identify and predict whether there is HAB occurrence in the region. A chlorophyll a concentration (Chl-a; mg/L) variable was used as an HAB indicator, where the data were obtained from MODIS and GEBCO bathymetry. The eight-day dataset interval was from January 2003 to December 2018. The results obtained showed that the LSTM model outperformed the CNN model in terms of accuracy using RMSE and the correlation coefficient r as the statistical criteria.

Recently, an increase in wildfire incidents has caused significant damage from economical, humanitarian, and environmental perspectives. Wildfires have increased in severity, frequency, and duration because of climate change and rising global temperatures, resulting in the release of massive volumes of greenhouse gases, the destruction of forests and associated habitats, and the damage to infrastructures. Therefore, identifying burned areas is crucial for monitoring wildfire damage. In this study, we aim at detecting forest burned areas occurring in South Korea using optical satellite images. To exploit the advantage of applying machine learning, the present study employs representative three machine learning methods, Light Gradient Boosting Machine (LightGBM), Random Forest (RF), and U-Net, to detect forest burned areas with a combination of input variables, namely Surface Reflectance (SR), Normalized Difference Vegetation Index (NDVI), and Normalized Burn Ratio (NBR). Two study sites of recently occurred forest fire events in South Korea were selected, and Sentinel-2 satellite images were used by considering a small scale of the forest fires. The quantitative and qualitative evaluations according to the machine learning methods and input variables were carried out. In terms of the comparison focusing on machine learning models, the U-Net showed the highest accuracy in both sites amongst the designed variants. The pre and post fire images by SR, NDVI, NBR, and difference of indices as the main inputs showed the best result. We also demonstrated that diverse landcovers may result in a poor burned area detection performance by comparing the results of the two sites.

Traditional in situ observation interpolation techniques that provide rainfall data from rain gauges have limitations because they are discrete point-based data records, which may not be sufficient to assess droughts from a spatiotemporal perspective. Considering this limitation, this study has developed a run-off model—a fully satellite-based method for monitoring drought in Peninsular Malaysia. The formulation of the run-off deficit uses a water balance equation based on satellite-based rainfall and evapotranspiration data extracted respectively from calibrated TRMM multi-satellites precipitation analysis data (TMPA) and moderate resolution imaging spectroradiometer data (MODIS). The run-off deficit was calculated based on per pixel spatial scale and allowed to produce the continuous and regular run-off maps. The run-off model was tested and evaluated in a one drought year (2005) within a span of three years (2003–2005) over the Kelantan (3448 km²) and Hulu Perak (3672 km²) catchments of Peninsular Malaysia. The validation results show that (1) monthly TMPA rainfall and MODIS evapotranspiration data significantly improved after calibration; (2) satellite-based run-off data is not only strongly correlated with actual steam flow, but also with spatiotemporal variation of run-off in drought-affected forest catchments. The most severely drought-affected forest catchments that experienced the run-off deficits were Hulu Perak, Ulu Gading, Gunung Stong and Relai over Kelantan. The real time run-off change analysis shows that drought started in January and reached its peak in July of 2005. It was therefore demonstrated that this fully satellite-based run-off deficit model is as good as a conventional drought-monitoring indicator, and can provide not only drought distribution information, but it also can reflect the drought-induced impacts on stream flow, forest catchment and land-use.

One of the largest hydropower facilities currently in operation in Malaysia is the Terengganu hydroelectric facility. As a result, for hydropower generation to be sustainable, future water availability in hydropower plants must be known. Therefore, it is necessary to precisely estimate how the river flow will alter as a result of changing rainfall patterns. Finding the best value for the hyper-parameters is one of the problems with machine learning algorithms, which have lately been adopted by many academics. In this research, Artificial Neural Network (ANN) is integrated with a nature-inspired optimizer, namely Cuckoo search algorithm (CS-ANN). The performance of the proposed algorithm then will be examined based on statistical indices namely Root-Mean-Square Error (RSME) and Determination Coefficient (R²). Then, the accuracy of the proposed model will be then examined with the stand-alone Artificial Neural Network (ANN). The statistical indices results indicate that the proposed Hybrid CS-ANN model showed an improvement based on R² value as compared to ANN model with R² of 0.900 at training stage and R² of 0.935 at testing stage. RMSE value, for ANN model, is 127.79 m³/s for training stage and 12.7 m³/s at testing stage. While for the proposed Hybrid CS-ANN model, RMSE value is equal to 121.7 m³/s for training stage and 10.95 m³/s for testing stage. The results revealed that the proposed model outperformed the stand-alone model in predicting the river flow with high level of accuracy. Although the proposed model could be applied in different case study, there is a need to tune the model internal parameters when applied in different case study.

In this study, half-hourly Global Precipitation Mission (GPM) satellite precipitation data were downscaled to produce high-resolution daily rainfall data for tropical coastal micro-watersheds (100–1000 ha) without gauges or with rainfall data conflicts. Currently, daily-scale satellite rainfall downscaling techniques rely on rain gauge data as corrective and controlling factors, making them impractical for ungauged watersheds or watersheds with rainfall data conflicts. Therefore, we used high-resolution local orographic and vertical velocity data as proxies to downscale half-hourly GPM precipitation data (0.1°) to high-resolution daily rainfall data (0.02°). The overall quality of the downscaled product was similar to or better than the quality of the raw GPM data. The downscaled rainfall dataset improved the accuracy of rainfall estimates on the ground, with lower error relative to measured rain gauge data. The average error was reduced from 41 to 27 mm/d and from 16 to 12 mm/d during the wet and dry seasons, respectively. Estimates of localized rainfall patterns were improved from 38% to 73%. The results of this study will be useful for production of high-resolution satellite precipitation data in ungauged tropical micro-watersheds.

Since ortho-image constructed from unmanned aerial vehicles (UAV) acquired images has significant misalignment effect, an optimized and precise workflow (WF) is proposed in this study. Based on the parameters of photo alignment, sparse point cloud model, blending and seamline refinement, the 24 combinations of ortho-image producing methods were tested. The optimal WF is evaluated from the aspects of coral mapping accuracy, geometric fidelity, completeness, and efficiency. Statistical error analysis shows that blending and seamline refinement are the most relevant WF components that influence accuracy of orthorectification and consequently coral reef classification. The optimal WF found to be when ‘highest’ photo alignment, with ‘high’ tie points in the sparse cloud model are applied, in presence of blending and seamline refinements and can achieve 87.9% overall mapping accuracy. With the available photogrammetric software packages, the proposed WF can be used in mosaicking and mapping large scale macroalgae, seagrass and seaweed.