Social sustainability and collaborative learning

The social dimension is central to sustainable development of agri-food systems. If farmers are not satisfied with their situation or motivated to continue farming, many of today's environmental goals will be impossible to achieve. Between 1997 and 2003, several case studies were carried out on social sustainability, the importance of recognition in the farming system, and the potential role of increased collaboration between actors. The main hypothesis was that improved recognition is a basis for sustainable social conditions. Our findings show that many farmers today perceive an impoverished social situation. They believe they lack control over decisions, which hinders their ability to continue farming. Public images and political decisions show a lack of respect for farmers' skills and knowledge. However, increased collaboration among actors is believed to be one important way forward, creating stronger relationships and networks, as well as a stronger identity for farmers. Our findings emphasize the need for authorities and other organizations to support farmers and to facilitate collaborative learning and decision-making processes for socioecological sustainability.     

Influencing factors of carbon emissions and their trends in China and India: a machine learning method

China and India are the largest coal consumers and the most populated countries in the world. With industrial and population growth, the need for energy has increased, which has inevitably led to an increase in carbon dioxide (CO₂) emissions because both countries depend on fossil fuel consumption. This paper investigates the impact of energy consumption, financial development (FD), gross domestic product (GDP), population, and renewable energy on CO₂ emissions. The study applies the long short-term memory (LSTM) method, a novel machine learning (ML) approach, to examine which influencing driver has the greatest and smallest impact on CO₂ emissions; correspondingly, this study builds a model for CO₂ emission reduction. Data collected between 1990 and 2014 were analyzed, and the results indicated that energy consumption had the greatest effect and renewable energy had the smallest impact on CO₂ emissions in both countries. Subsequently, we increased the renewable energy coefficient by one and decreased the energy consumption coefficient by one while keeping all other factors constant, and the results predicted with the LSTM model confirmed the significant reduction in CO₂ emissions. Finally, this study forecasted a CO₂ emission trend, with a slowdown predicted in China by 2022; however, CO₂ emission’s reduction is not possible in India until 2023. These results suggest that shifting from nonrenewable to renewable sources and lowering coal consumption can reduce CO₂ emissions without harming economic development.

     

Integration of the environment in product design by a learning process: proposal for a piloting tool

This paper examines the nature of ecological economics, arguing that it comprises two aspects, the qualitative framework within which it operates and the quantitative techniques which it uses to measure sustainability, evaluate policies and assist decision-making. The former is distinct to ecological economics, whereas the latter is largely shared with environmental economics. Although these have co-existed for some time, it is contended that the qualitative aspect needs to be developed if ecological economics is to realise its potential. The paper first offers a Schumpeterian 'pre-analytic' vision of ecological economics. Ecological economics, it is argued, necessarily implies a fundamental change in the way problems are perceived and in how they should be addressed. Second, the paper discusses the quantitative aspect of ecological economics, arguing that the overlap with environmental economics in the techniques used is one reason why the two have frequently not been seen as sufficiently distinct. The paper concludes that a development of the qualitative, procedural aspect of ecological economics is needed if its full potential for influencing policy-making is to be realised.     

Pollution,economic growth,and COVID-19 deaths in India: a machine learning evidence

Environmental Science and Pollution Research - This study uses two different approaches to explore the relationship between pollution emissions, economic growth, and COVID-19 deaths in India. Using...     

Spatio-temporal classification and prediction of land use and land cover change for the Vembanad Lake system,Kerala: a machine learning approach

Environmental Science and Pollution Research - Land use and land cover (LULC) change has become a critical issue for decision planners and conservationists due to inappropriate growth and its...     

Ecological literacy and beyond: Problem-based learning for future professionals

Ecological science contributes to solving a broad range of environmental problems. However, lack of ecological literacy in practice often limits application of this knowledge. In this paper, we highlight a critical but often overlooked demand on ecological literacy: to enable professionals of various careers to apply scientific knowledge when faced with environmental problems. Current university courses on ecology often fail to persuade students that ecological science provides important tools for environmental problem solving. We propose problem-based learning to improve the understanding of ecological science and its usefulness for real-world environmental issues that professionals in careers as diverse as engineering, public health, architecture, social sciences, or management will address. Courses should set clear learning objectives for cognitive skills they expect students to acquire. Thus, professionals in different fields will be enabled to improve environmental decision-making processes and to participate effectively in multidisciplinary work groups charged with tackling environmental issues.     

Deep learning architecture for air quality predictions

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.     

Susceptibility mapping of groundwater salinity using machine learning models

Environmental Science and Pollution Research - Increasing groundwater salinity has recently raised severe environmental and health concerns around the world. Advancement of the novel methods for...     

Forecasting air quality time series using deep learning

This paper presents one of the first applications of deep learning (DL) techniques to predict air pollution time series. Air quality management relies extensively on time series data captured at air monitoring stations as the basis of identifying population exposure to airborne pollutants and determining compliance with local ambient air standards. In this paper, 8 hr averaged surface ozone (O₃) concentrations were predicted using deep learning consisting of a recurrent neural network (RNN) with long short-term memory (LSTM). Hourly air quality and meteorological data were used to train and forecast values up to 72 hours with low error rates. The LSTM was able to forecast the duration of continuous O₃ exceedances as well. Prior to training the network, the dataset was reviewed for missing data and outliers. Missing data were imputed using a novel technique that averaged gaps less than eight time steps with incremental steps based on first-order differences of neighboring time periods. Data were then used to train decision trees to evaluate input feature importance over different time prediction horizons. The number of features used to train the LSTM model was reduced from 25 features to 5 features, resulting in improved accuracy as measured by Mean Absolute Error (MAE). Parameter sensitivity analysis identified look-back nodes associated with the RNN proved to be a significant source of error if not aligned with the prediction horizon. Overall, MAE's less than 2 were calculated for predictions out to 72 hours.

Implications: Novel deep learning techniques were used to train an 8-hour averaged ozone forecast model. Missing data and outliers within the captured data set were replaced using a new imputation method that generated calculated values closer to the expected value based on the time and season. Decision trees were used to identify input variables with the greatest importance. The methods presented in this paper allow air managers to forecast long range air pollution concentration while only monitoring key parameters and without transforming the data set in its entirety, thus allowing real time inputs and continuous prediction.     

Prediction of effluent arsenic concentration of wastewater treatment plants using machine learning and kriging-based models

Environmental Science and Pollution Research - This study evaluates the potential of kriging-based (kriging and kriging-logistic) and machine learning models (MARS, GBRT, and ANN) in predicting the...     

Moving to sustainability by learning from successful fisheries

There are two diverging views of the status and future of the world's fisheries. One group represented largely by academic marine ecologists sees almost universal failure of fisheries management and calls for the use of marine-protected areas as the central tool of a new approach to rebuilding the marine ecosystems of the world. The scientists working in fisheries agencies and many academic scientists see a more complex picture, with many failed fisheries but also numerous successes. This group argues that we need to apply the lessons from the successful fisheries to stop the decline and rebuild those fisheries threatened by excess fishing. These lessons are stopping the competitive race to fish by appropriate incentives for fishing fleets and good governance. The major tool of resetting incentives is granting various forms of dedicated access, including community-based fishing rights, allocation to cooperatives, and individual fishing quotas. Many of the failed fisheries of the world occur in jurisdictions where central governments are not functional, and local control of fisheries is an essential part of the solution.     

Urban transport and land-use policies in East and West: learning from experience?

This paper considers the implications of changing land use and transport patterns in cities in Central and Eastern Europe. It reviews experience elsewhere, primarily in Western Europe, where a spiral of increasing mobility and dispersal is widely acknowledged to be environmentally, socially and economically unsustainable. Policies being adopted at different scales in attempts to modify these trends are outlined, and some considerations for CEE cities are highlighted. It is argued that sustainable land use and transport systems are a matter of political choice.     

Extreme learning machines: a new approach for modeling dissolved oxygen (DO) concentration with and without water quality variables as predictors

In this paper, several extreme learning machine (ELM) models, including standard extreme learning machine with sigmoid activation function (S-ELM), extreme learning machine with radial basis activation function (R-ELM), online sequential extreme learning machine (OS-ELM), and optimally pruned extreme learning machine (OP-ELM), are newly applied for predicting dissolved oxygen concentration with and without water quality variables as predictors. Firstly, using data from eight United States Geological Survey (USGS) stations located in different rivers basins, USA, the S-ELM, R-ELM, OS-ELM, and OP-ELM were compared against the measured dissolved oxygen (DO) using four water quality variables, water temperature, specific conductance, turbidity, and pH, as predictors. For each station, we used data measured at an hourly time step for a period of 4 years. The dataset was divided into a training set (70%) and a validation set (30%). We selected several combinations of the water quality variables as inputs for each ELM model and six different scenarios were compared. Secondly, an attempt was made to predict DO concentration without water quality variables. To achieve this goal, we used the year numbers, 2008, 2009, etc., month numbers from (1) to (12), day numbers from (1) to (31) and hour numbers from (00:00) to (24:00) as predictors. Thirdly, the best ELM models were trained using validation dataset and tested with the training dataset. The performances of the four ELM models were evaluated using four statistical indices: the coefficient of correlation (R), the Nash-Sutcliffe efficiency (NSE), the root mean squared error (RMSE), and the mean absolute error (MAE). Results obtained from the eight stations indicated that: (i) the best results were obtained by the S-ELM, R-ELM, OS-ELM, and OP-ELM models having four water quality variables as predictors; (ii) out of eight stations, the OP-ELM performed better than the other three ELM models at seven stations while the R-ELM performed the best at one station. The OS-ELM models performed the worst and provided the lowest accuracy; (iii) for predicting DO without water quality variables, the R-ELM performed the best at seven stations followed by the S-ELM in the second place and the OP-ELM performed the worst with low accuracy; (iv) for the final application where training ELM models with validation dataset and testing with training dataset, the OP-ELM provided the best accuracy using water quality variables and the R-ELM performed the best at all eight stations without water quality variables. Fourthly, and finally, we compared the results obtained from different ELM models with those obtained using multiple linear regression (MLR) and multilayer perceptron neural network (MLPNN). Results obtained using MLPNN and MLR models reveal that: (i) using water quality variables as predictors, the MLR performed the worst and provided the lowest accuracy in all stations; (ii) MLPNN was ranked in the second place at two stations, in the third place at four stations, and finally, in the fourth place at two stations, (iii) for predicting DO without water quality variables, MLPNN is ranked in the second place at five stations, and ranked in the third, fourth, and fifth places in the remaining three stations, while MLR was ranked in the last place with very low accuracy at all stations. Overall, the results suggest that the ELM is more effective than the MLPNN and MLR for modelling DO concentration in river ecosystems.     

Modelling of ecological status of Polish lakes using deep learning techniques

Environmental Science and Pollution Research - Since 2000, after the Water Framework Directive came into force, aquatic ecosystems’ bioassessment has acquired immense practical importance for...     

Pre- and post-dam river water temperature alteration prediction using advanced machine learning models

Environmental Science and Pollution Research - Dams significantly impact river hydrology by changing the timing, size, and frequency of low and high flows, resulting in a hydrologic regime that...     

Proposed formulation of surface water quality and modelling using gene expression,machine learning,and regression techniques

Environmental Science and Pollution Research - The rising water pollution from anthropogenic factors motivates further research in developing water quality predicting models. The available models...     

Applicability of hybrid bionic optimization models with kernel-based extreme learning machine algorithm for predicting daily reference evapotranspiration: a case study in arid and semiarid regions,China

Environmental Science and Pollution Research - The accurate prediction of daily reference crop evapotranspiration (ETO) enables effective management decision-making for agricultural water...     

Unmanned aerial vehicle images in the machine learning for agave detection

Environmental Science and Pollution Research - In this study, six supervised classification algorithms were compared. The algorithms were based on cluster analysis, distance, deep learning, and...     

Application of ensemble machine learning model in downscaling and projecting climate variables over different climate regions in Iran

Environmental Science and Pollution Research - This study evaluates the future climate fluctuations in Iran’s eight major climate regions (G1–G8). Synoptic data for the period...     

Evaluation of deep learning and transform domain feature extraction techniques for land cover classification: balancing through augmentation

Environmental Science and Pollution Research - The identification of features that can improve classification accuracy is a major concern in land cover classification research. This paper compares...