Sustainability

25 pages, 4660 KiB

Open AccessArticle

CO Emission Prediction Based on Kernel Feature Space Semi-Supervised Concept Drift Detection in Municipal Solid Waste Incineration Process

by Runyu Zhang, Jian Tang and Tianzheng Wang

Sustainability 2025, 17(13), 5672; https://doi.org/10.3390/su17135672 (registering DOI) - 20 Jun 2025

Abstract

Carbon monoxide (CO) is a toxic pollutant emitted by municipal solid waste incineration (MSWI), which has a strong correlation with dioxins. In terms of the sustainable development of an ecological environment, CO emission concentration is strictly controlled by the environmental departments of various countries in the world. The construction of its prediction model is conducive to pollution reduction control. The MSWI process is affected by multi-factors such as MSW component fluctuation, equipment wear and maintenance, and seasonal change, and has complex nonlinear and time-varying characteristics, which makes it difficult for the CO prediction model based on offline historical data to adapt to the above changes. In addition, the continuous emission monitoring system (CEMS) used for conventional pollutant detection has unavoidable misalignment and failure problems. In this article, a novel prediction model of CO emission from the MSWI process based on semi-supervised concept drift (CD) detection in kernel feature space is proposed. Firstly, the CO emission deep prediction model and the kernel feature space detection model are constructed based on offline batched historical data, and the historical data set for the real-time construction of the pseudo-labeling model is obtained. Secondly, the drift detection for the CO emission prediction model is carried out based on real-time data by using unsupervised kernel principal component analysis (KPCA) in terms of feature space. If CD occurs, the pseudo-label model is constructed, the pseudo-truth value is obtained, and the drift sample is confirmed and selected based on the Page–Hinkley (PH) test. If no CD occurs, the CO emission concentration is predicted based on the historical prediction model. Then, the updated data set of the CO emission prediction model and kernel feature space detection is obtained by combining historical samples and drift samples. Finally, the offline history model is updated with a new data set when the preset conditions are met. Based on the real data set of an MSWI power plant in Beijing, the validity of the proposed method is verified. Full article

(This article belongs to the Special Issue Novel and Scalable Technologies for Sustainable Waste Management)

► Show Figures

Figure 1

12 pages, 2911 KiB

Open AccessArticle

Supporting Sustainable Development Through Early-Life DRR Learning Opportunities: UK School Insights

by Maciej Pawlik and Kaori Kitagawa

Sustainability 2025, 17(13), 5671; https://doi.org/10.3390/su17135671 (registering DOI) - 20 Jun 2025

Abstract

The increasing frequency and intensity of extreme environmental phenomena mandate further actions to protect the most vulnerable groups, especially children. Traditionally, children have been excluded from conversations about disasters; however, this exclusion is reductive and perpetuates false ideas about children’s capacity to engage with safety information and materially manifest sustainable practices in their life. Such a reality is also impractical because early exposure through learning opportunities can yield engagement in sustainable development in adulthood. This research sought to improve understanding about children’s capacity to engage in DRR information. This study reviewed posters created by 7-year-old children at a primary school in the UK. These were produced as part of prior climate change workshops and included an illustration of a flood safety kit with items children would choose to have with them if there was an emergency (e.g., flooding event). Items included were counted and tallied to identify trends. The results demonstrated the capacity of children in this age group to select practically useful items for their safety in flooding emergencies. Based on findings, this study advocates for greater inclusion of children within disaster preparedness activities and the production of more tailored DRR learning opportunities to engage children within their school environment. Full article

(This article belongs to the Special Issue Developing Sustainable Participation in Learning for Disaster Risk Reduction and Climate Resilience)

► Show Figures

Figure 1

18 pages, 1208 KiB

Open AccessArticle

Environmental Sustainability of Nile Tilapia Reared in Biofloc Technology (BFT) System: Evaluation of Carbon, Nitrogen, and Phosphorus Dynamics and Indicators of Sustainability

by Tainara Laise da Silva Blatt, Alex Júnio da Silva Cardoso, André Luiz Watanabe, Celso Carlos Buglione Neto and Hamilton Hisano

Sustainability 2025, 17(13), 5670; https://doi.org/10.3390/su17135670 (registering DOI) - 20 Jun 2025

Abstract

This study aimed to evaluate the dynamics of total carbon (TC), total nitrogen (TN), total phosphorus (TP), and some indicators of environmental sustainability of Nile tilapia reared in a biofloc technology (BFT) system. Nile tilapia fingerlings were cultured in three BFT units of production (4.2 m³ each) at a stocking density of 395 fish/m³. After 70 days, the survival rate was 98.05%, with a final average weight of 20.43 g, and apparent feed conversion of 1.05. Nutrient inputs were from supply water, initial fish biomass, and feed; outputs were measured from the final fish biomass and effluent. TC, TN, and TP concentrations in the water increased linearly over time (p < 0.001) by 1.54, 1.66, and 0.44 mg/L, respectively. Feed contributed over 88% of nutrient inputs, while fish final biomass accounted for over 50% of output. Nutrient retention in fish final biomass was 29.74% (TC), 45.38% (TN), and 46.34% (TP). The system had low eutrophication potential, estimated at 57.39 kg TC, 20.02 kg TN, and 5.70 kg TP per ton of fish. Water use was minimal (0.0074 m³/ton), but energy demand was high (114.59 MJ/kg). The closed system reduces biodiversity risks by preventing fish escape. In conclusion, BFT supports high fish productivity with efficient nutrient use, minimal water use, and limited environmental impact, contributing to environmentally sustainable aquaculture. Full article

► Show Figures

Figure 1

23 pages, 2278 KiB

Open AccessArticle

The Evolution of Ecological Well-Being Performance and Its Effects on Population Longevity: A County-Level Spatiotemporal Analysis of Hubei Province, China

by Jinbo Yan, Rongjun Ao, Xiaoqi Zhou and Jing Jiang

Sustainability 2025, 17(13), 5669; https://doi.org/10.3390/su17135669 (registering DOI) - 20 Jun 2025

Abstract

Building an ecological civilization and promoting national health are crucial for high-quality development. These goals are linked to ecological well-being performance (EWP). This study aimed to evaluate EWP based on county-scale input–output relationships, analyze its spatiotemporal evolution, and explore how EWP changes affect longevity through spatial spillover and interaction mechanisms. We first used the super-SBM model to assess county-level EWP from 2000 to 2020. Then, spatial econometric models and geographical detectors were applied to analyze the impact of EWP on longevity. The results show a persistent uptrend in overall EWP, indicating that Hubei Province has enhanced its sustainable development capacity. Regions with high EWP values have distinct characteristics. There is polarization in the east, expansive connectivity in the west, and fragmentation in the center, forming a clear “core–edge” structure. The improvement in EWP directly promotes male, female, and overall population longevity and has spatial spillover effects. EWP also interacts with the natural environment and socioeconomic development, serving as a key factor promoting population longevity within Hubei Province. These findings provide a reference for regions in China or other developing countries to understand the relationships between the extension of population lifespan and regional sustainable development. Full article

(This article belongs to the Special Issue Ecosystem Services and Sustainable Development of Human Health)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sustainability, Volume 17, Issue 13 (July-1 2025) – 4 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI