Facing the big data wave, this study applied artificial intelligence to cite knowledge and find a feasible process to play a crucial role in supplying innovative value in environmental education. Intelligence agents of artificial intelligence and natural language processing (NLP) are two key areas leading the trend in artificial intelligence; this research adopted NLP to analyze the research topics of environmental education research journals in the Web of Science (WoS) database during 2011–2020 and interpret the categories and characteristics of abstracts for environmental education papers. The corpus data were selected from abstracts and keywords of research journal papers, which were analyzed with text mining, cluster analysis, latent Dirichlet allocation (LDA), and co-word analysis methods. The decisions regarding the classification of feature words were determined and reviewed by domain experts, and the associated TF-IDF weights were calculated for the following cluster analysis, which involved a combination of hierarchical clustering and K-means analysis. The hierarchical clustering and LDA decided the number of required categories as seven, and the K-means cluster analysis classified the overall documents into seven categories. This study utilized co-word analysis to check the suitability of the K-means classification, analyzed the terms with high TF-IDF wights for distinct K-means groups, and examined the terms for different topics with the LDA technique. A comparison of the results demonstrated that most categories that were recognized with K-means and LDA methods were the same and shared similar words; however, two categories had slight differences. The involvement of field experts assisted with the consistency and correctness of the classified topics and documents.

Water deficit during the growing season is a major factor limiting vegetable production. Therefore, saving water used for vegetable production by applying regulated deficit irrigation (RDI) can be a strategy to reduce water supply. The effects of different RDI levels from irrigation systems on vegetable yields, yield components, water use, and water use efficiency (WUE) of maize, lettuce, and garland chrysanthemum were investigated in a pot experiment. Plants were subjected to four irrigation levels, as follows: full irrigation as a control (RDI-100), 70% of full irrigation (RDI-70), 50% of full irrigation (RDI-50), and 30% of full irrigation (RDI-30). The WUE values of maize and lettuce were significantly higher with RDI-30 than other treatments, yet a significant reduction of WUE in garland chrysanthemum was detected compared to other treatments. There were significant correlations of WUEi with WUEyield and WUEbiomass in maize plants, indicating that WUEi can be a useful nondestructive estimator of yields and biomass contents in maize. Moreover, a significant correlation between WUEi and WUEyield in lettuce plants was observed. This index was correlated with economic production, and can be used to assess fresh weights and as an index of the irrigated water content. These results for evaluating water deficits in plants used nondestructive measurements that are applicable to large-scale water management of vegetable plants, thereby enabling scarce water resources to be conserved.

Public understanding of complex sustainability concepts like life cycle assessment (LCA) is crucial for promoting environmentally responsible consumption yet remains a significant educational challenge. This study introduces and evaluates Paper Goes Green, a competitive board game designed to make abstract LCA principles tangible and personally relevant. The game simulates the paper production chain, compelling players to make strategic decisions about resource allocation, production pathways (conventional vs. green), and waste management to fulfill paper orders. Through a single-group pre-test/post-test design with 85 participants (25 environmental educators and 60 public members), the game’s efficacy was assessed. Paired-sample t-tests revealed significant improvements in participants’ perceived knowledge of green chemistry/LCA (pre-game mean 2.05, post-game 3.24 on a 5-point scale, p < 0.001), pro-environmental attitudes (3.38 to 4.22, p < 0.001), and behavioral intentions toward green consumption (3.97 to 4.44, p < 0.001). These gains correspond to medium-to-large effect sizes (Cohen’s d = 0.94 for knowledge, 0.70 for attitude, 0.71 for behavior), indicating substantial practical impact. Qualitative feedback further highlighted the game’s engaging and thought-provoking nature. Notably, specific design features—such as immediate feedback, player control, and interactivity—were identified as key contributors to learning, fostering systems thinking in players. These findings suggest that Paper Goes Green is a promising educational tool for translating complex environmental science into an engaging, impactful learning experience. The game effectively bridges the gap between abstract concepts and real-world consumer choices, fostering life cycle thinking and empowering players to make greener choices in their daily lives.