Enhancing environmental monitoring of harmful algal blooms with ConvLSTM image prediction

This study advances environmental monitoring by predicting the spatial and temporal distribution of Harmful Algal Blooms (HABs) in the Republic of Korea through a hybrid approach that combines geostatistical and deep learning methods. Using 3D universal kriging, the study interpolates missing HAB concentration values, transforming geospatial point data into spatially continuous grid images that serve as the foundation for predictive modeling. These interpolated images are then used as input for a ConvLSTM (Convolutional Long Short-Term Memory) network, which integrates convolutional layers to capture spatial patterns and LSTM units to model temporal dependencies. By leveraging this spatiotemporal modeling framework, the ConvLSTM network effectively predicts future HAB concentrations with improved accuracy. This innovative methodology highlights the utility of combining 3D universal kriging for spatial interpolation with image-based ConvLSTM prediction, offering valuable insights into HAB dynamics and supporting sustainable strategies for environmental management and public health.