A greenhouse research study was conducted at Eastern New Mexico University, Portales, NM, USA, in 2019 to examine the effects of different nutrient solutions on the growth and weight of two lettuce cultivars grown in a floating hydroponic system. Two lettuce cultivars, Buttercrunch and Black Seeded Simpson, were subjected to one of four different nutrient concentrations of N, K and Ca at 150, 100, and 150 ppm (N1), 210, 235, and 200 ppm (N2), 250, 300 and 250 ppm (N3), and 300, 350, and 350 ppm (N4), respectively. The Buttercrunch cultivar and N3 treatment proved significantly more productive than the other cultivar/treatment combinations. The greatest fresh weights were recorded in the N3 nutrient solution, 115.33 and 93.17 g/plant for Buttercrunch and Black Seeded Simpson, respectively. Buttercrunch had the greatest fresh weight, leaf number, and leaf and root length in all nutrient solutions. The nitrogen content of the solutions showed a significant positive relationship with chlorophyll content for both cultivars. It is expected that the development of a cheap and easy-to-use hydroponic system will help growers produce high-quality organic vegetables including lettuce.

Prediction of water quality is a critical aspect of water pollution control and prevention. The trend of water quality can be predicted using historical data collected from water quality monitoring and management of water environment. The present study aims to develop a long short-term memory (LSTM) network and its attention-based (AT-LSTM) model to achieve the prediction of water quality in the Burnett River of Australia. The models developed in this study introduced an attention mechanism after feature extraction of water quality data in the section of Burnett River considering the effect of the sequences on the prediction results at different moments to enhance the influence of key features on the prediction results. This study provides one-step-ahead forecasting and multistep forward forecasting of dissolved oxygen (DO) of the Burnett River utilizing LSTM and AT-LSTM models and the comparison of the results. The research outcomes demonstrated that the inclusion of the attention mechanism improves the prediction performance of the LSTM model. Therefore, the AT-LSTM-based water quality forecasting model, developed in this study, demonstrated its stronger capability than the LSTM model for informing the Water Quality Improvement Plan of Queensland, Australia, to accurately predict water quality in the Burnett River.