Optimization of deep learning model for coastal chlorophyll a dynamic forecast

Improving algal bloom detection using spectroscopic analysis and machine learning: A case study in a large artificial reservoir, South Korea

The prediction of algal blooms using traditional water quality indicators is expensive, labor-intensive, and time-consuming, making it challenging to meet the critical requirement of timely monitoring for prompt management. Using optical measures for forecasting algal blooms is a feasible and useful method to overcome these problems. This study explores the potential application of optical measures to enhance algal bloom prediction in terms of prediction accuracy and workload reduction, aided by machine learning (ML) models. Compared to absorption-derived parameters, commonly used fluorescence indices such as the fluorescence index (FI), humification index (HIX), biological index (BIX), and protein-like component improved the prediction accuracy. However, the prediction accuracy was decreased when all optical indices were considered for computation due to increased noise and uncertainty in the models. With the exception of chemical oxygen demand (COD), this study successfully replaced biochemical oxygen demand (BOD), dissolved organic carbon (DOC), and nutrients with selected fluorescence indices, demonstrating relatively analogous performance in either training or testing data, with consistent and good coefficient of determination (R2) values of approximately 0.85 and 0.74, respectively. Among all models considered, ensemble learning models consistently outperformed conventional regression models and artificial neural networks (ANNs). However, there was a trade-off between accuracy and computation efficiency among the ensemble learning models (i.e., Stacking and XGBoost) for algal bloom prediction. Our study offers a glimpse of the potential application of spectroscopic measures to improve accuracy and efficiency in algal bloom prediction, but further work should be carried out in other water bodies to further validate our proposed hypothesis.

Design of a Greenhouse Solar-Assisted Heat Pump Dryer for Kelp (Laminaria japonica): System Performance and Drying Kinetics

In order to solve a series of problems with kelp drying including long drying time, high energy consumption, low drying efficiency, and poor quality of dried kelp, this work proposes the design of a novel greenhouse double-evaporator solar-assisted heat pump drying system. Experiments on kelp solar-assisted heat pump drying (S-HP) and heat pump drying (HP) under the condition of irradiance of 100-700 W/m2 and a temperature of 30, 40, or 50 °C were conducted and their results were compared in terms of system performance, drying kinetics, and quality impact. The drying time was reduced with increasing irradiance or temperature. The coefficient of performance (COP) and specific moisture extraction rate (SMER) of S-HP were 3.590-6.810, and 1.660-3.725 kg/kW·h, respectively, roughly double those of HP when the temperatures are identical. The Deff of S-HP and HP were 5.431 × 10-11~11.316 × 10-11 m2/s, and 1.037 × 10-11~1.432 × 10-11 m2/s, respectively; additionally, solar radiation greatly improves Deff. The Page model almost perfectly described the changes in the moisture ratio of kelp by S-HP and HP with an inaccuracy of less than 5%. When the temperature was 40 °C and the irradiance was above 400 W/m2, the drying time of S-HP was only 3 h, and the dried kelp maintained the green color with a strong flavor and richness in mannitol. Meanwhile, the coefficient of performance was 6.810, the specific moisture extraction rate was 3.725 kg/kWh, and the energy consumption was 45.2%, lower than that of HP. It can be concluded that S-HP is highly efficient and energy-saving for macroalgae drying and can serve as an alternate technique for the drying of other aquatic products.