Machine Learning and Big Data Analytics for Sustainability and Resilience

The need for robust rainfall estimation has increased with more frequent and intense floods due to human-induced land use and climate change, especially in urban areas. Besides the existing rainfall measurement systems, citizen science can offer unconventional methods to provide complementary rainfall data for enhancing spatial and temporal data coverage. This demand for accurate rainfall data is particularly crucial in the context of smart city innovations, where real-time weather information is essential for effective urban planning, flood management, and environmental sustainability. Therefore, this study provides proof-of-concept for a novel method of estimating rainfall intensity using its recorded audio in an urban area, which can be incorporated into a smart city as part of its real-time weather forecasting system. This study proposes a convolutional neural network (CNN) inversion model for acoustic rainfall intensity estimation. The developed CNN rainfall sensing model showed a significant improvement in performance over the traditional approach, which relies on the loudness feature as an input, especially for simulating rainfall intensities above 60 mm/h. Also, a CNN-based denoising framework was developed to attenuate unwanted noises in rainfall recordings, which achieved up to 98% accuracy on the validation and testing datasets. This study and its promising results are a step towards developing an acoustic rainfall sensing tool for citizen-science applications in smart cities. However, further investigation is necessary to upgrade this proof-of-concept for practical applications. Full article

Ensuring safe and clean drinking water for communities is crucial, and necessitates effective tools to monitor and predict water quality due to challenges from population growth, industrial activities, and environmental pollution. This paper evaluates the performance of multiple linear regression (MLR) and nineteen machine learning (ML) models, including algorithms based on regression, decision tree, and boosting. Models include linear regression (LR), least angle regression (LAR), Bayesian ridge chain (BR), ridge regression (Ridge), k-nearest neighbor regression (K-NN), extra tree regression (ET), and extreme gradient boosting (XGBoost). The research’s objective is to estimate the surface water quality of Al-Seine Lake in Lattakia governorate using the MLR and ML models. We used water quality data from the drinking water lake of Lattakia City, Syria, during years 2021–2022 to determine the water quality index (WQI). The predictive performance of both the MLR and ML models was evaluated using statistical methods such as the coefficient of determination (R²) and the root mean square error (RMSE) to estimate their efficiency. The results indicated that the MLR model and three of the ML models, namely linear regression (LR), least angle regression (LAR), and Bayesian ridge chain (BR), performed well in predicting the WQI. The MLR model had an R² of 0.999 and an RMSE of 0.149, while the three ML models had an R² of 1.0 and an RMSE of approximately 0.0. These results support using both MLR and ML models for predicting the WQI with very high accuracy, which will contribute to improving water quality management. Full article

Climate change is harmful to ecosystems and public health, so the concern about climate change has been aroused worldwide. Studies indicated that greenhouse gas emission with $C{O}_2$ as the main component is an important factor for climate change. Countries worldwide are on the same page that low-carbon development is an effective way to combat climate change. Enhancing public concern about low-carbon development and climate change has a positive effect on universal participation in carbon emission reduction. Therefore, it is significant to study the trend of public concern about low carbon and its relationship with $C{O}_2$ emissions. Currently, no related studies are available, so this research explores the relationship between the public concern about low carbon and $C{O}_2$ emissions of China, as well as the respective trends of each. Based on the daily data of Baidu-related keyword searches and $C{O}_2$ emission, this research proposes the GMM-CEEMD-SGIA-LSTM hybrid model. The GMM is utilized to construct a comprehensive Baidu index (CBI) to reflect public concern about low carbon by clustering keywords search data. CEEMD and SGIA are applied to reconstruct sequences for analyzing the relationship between CBI and $C{O}_2$ emissions. Then LSTM is utilized to forecast CBI. The reconstructed sequences show that there is a strong correlation between CBI and $C{O}_2$ emissions. It is also found that CBI affects $C{O}_2$ emissions, with varying effect lag times for different periods. Compared to LSTM, RF, SVR, and RNN models, the proposed model is reliable for forecasting public concern with a 46.78% decrease in MAPE. The prediction results indicate that public concern about low carbon shows a fluctuating upward trend from January 2023 to January 2025. This research could improve understanding of the relationship between public concern about low carbon and $C{O}_2$ emissions to better address climate change. Full article

This study aimed to identify suitable sites for tea cultivation using both random forest and logistic regression models. The study utilized 2770 sample points to map the tea plantation suitability zones (TPSZs), considering 12 important conditioning factors, such as temperature, rainfall, elevation, slope, soil depth, soil drainability, soil electrical conductivity, base saturation, soil texture, soil pH, the normalized difference vegetation index (NDVI), and land use land cover (LULC). The data were normalized using ArcGIS 10.2 and the models were calibrated using 70% of the total data, while the remaining 30% of the data were used for validation. The final TPSZ map was classified into four different categories: highly suitable zones, moderately suitable zones, marginally suitable zones, and not-suitable zones. The study revealed that the random forest (RF) model was more precise than the logistic regression model, with areas under the curve (AUCs) of 85.2% and 83.3%, respectively. The results indicated that well-drained soil with a pH range between 5.6 and 6.0 is ideal for tea farming, highlighting the importance of climate and soil properties in tea cultivation. Furthermore, the study emphasized the need to balance economic and environmental considerations when considering tea plantation expansion. The findings of this study provide important insights into tea cultivation site selection and can aid tea farmers, policymakers, and other stakeholders in making informed decisions regarding tea plantation expansion. Full article

Studying resilience provides an opportunity to address a range of urban environmental problems. However, existing studies pay little attention to urban ecological resilience (UER), and the system of assessing urban resilience pays little attention to the process attribute of resilience. This study focuses on UER and constructs an evaluation framework based on the pressure _state _response (PSR) framework. The ‘pressure’ indicator morphological resilience (MR) is evaluated using source _sink landscape theory. The ‘state’ indicator density resilience (DR) is evaluated using the ratio of ecological carrying capacity to ecological footprint. The ‘response’ indicator uses indicators of economic structure, vitality, and innovation for evaluation. We found that the MR and DR of the study area in 2020 showed a spatial layout of low in the central area and high in the peripheral areas, while the high-value ER area was in the central part. The average district and county MR was 1.44, DR was between 0.003 and 1.975, and ER was 0.32; overall, ER and MR are better in the study area, but DR is worse. The spatial layout of comprehensive UER was found to be low in the middle and high in the periphery of the study area. Some areas with low MR and DR have high UER, which verifies the compensation effect of ER on urban ecology. This study provides a new method for assessing UER, and the findings can provide useful information for urban planning. Full article

Historically, the banking system has been critical to the development of economies by addressing funds efficiently—from customer savings and investors to the productive activities of people and companies, financing consumer goods and current expenses, housing, infrastructure projects and providing liquidity to the market. However, it must be transformed to respond to emerging demands in society for better financial products and services with a positive impact on living conditions and well-being. To achieve this, banks must create economic value—that is to say, banks should create profits in a sustained manner—in order to also create social value and thus generate shared value. The purpose of this study was twofold. The first aim was to identify the main factors that contributed to the majority of Mexican banking profits in the period from 2003 to 2021; the second aim of the study was to provide an innovative metric of banking performance. Using supervised machine learning algorithms and Principal Component Analysis, two prediction models were tested, and two banking performance indices were defined. The findings show that Random Forest is a reliable profit prediction model with a lower mean absolute error between the predicted yearly profit and losses and the actual data. There are no significant ranking position differences between the two performance indices. The first performance index obtained is novel due to its simplicity, since it is built on the basis of five values associated with commercial banking activity. In Mexico, no similar studies have been published. The indicator most widely used by regulators worldwide is the CAMELS index, which is a weighted average of the capital adequacy level, asset quality, management capacity, profitability, liquidity, and sensitivity to market risk. Its scale of 1 to 5 is useful for identifying the robustness and solvency of a bank, but not necessarily its capacity to generate profits. This approach might encourage banks to remain aware of their potential to create shared value and to develop competitive strategies to increase benefits for stakeholders. Full article

Wetlands are important habitats for biodiversity and provide ecosystem services such as climate mitigation and carbon storage. The current wetland mapping techniques in Norway are tedious and costly, and remote sensing provides an opportunity for large-scale mapping and ecosystem accounting. We aimed to implement a deep learning approach to mapping wetlands with Sentinel-2 and LiDAR data over southern Norway. Our U-Net model, implemented through Google Earth Engine and TensorFlow, produced a wetland map with a balanced accuracy rate of 90.9% when validated against an independent ground-truth sample. This represents an improvement upon manually digitized land cover maps in Norway, which achieved accuracy rates of 46.8% (1:50,000 map) and 42.4% (1:5000 map). Using our map, we estimated a total wetland coverage area of 12.7% in southern Norway, which is double the previous benchmark estimates (5.6%). We followed an iterative model training and evaluation approach, which revealed that increasing the quantity and coverage of labeled wetlands greatly increases the model performance. We highlight the potential of satellite-based wetland maps for the ecosystem accounting of changes in wetland extents over time—something that is not feasible with traditional mapping methods. Full article

Machine learning (ML) has seen a substantial increase in its role in improving operations for staff and customers in different industries. However, there appears to be a somewhat limited adoption of ML by farm businesses, highlighted by a review of the literature investigating innovative behaviors by rural businesses. A review of the literature identified a dearth of studies investigating ML adoption by farm businesses in rural regions of the United Arab Emirates (UAE), especially in the context of family-owned farms. Therefore, this paper aims to investigate the drivers and barriers to ML adoption by family/non-family-owned farms in rural UAE. The key research questions are (1) what are the drivers and barriers for rural UAE farms adopting ML? As well as (2) is there a difference in the drivers and barriers between family and non-family-owned farms? Twenty semi-structured interviews were conducted with farm businesses across several rural regions in the UAE. Then, through a Template Analysis (TA), drivers and barriers for rural UAE-based farm owners adopting ML were identified. Interview findings highlighted that farms could benefit from adopting ML in daily operations to save costs and improve efficiency. However, 16 of 20 farms were unaware of the benefits related to ML due to access issues (highlighted by 12 farms) in incorporating ML operations, where they felt that incorporating ML into their operations was costly (identified by 8 farms). It was also identified that non-family-owned farms were more likely to take up ML, which was attributed to local culture influencing family farms (11 farms identified culture as a barrier). This study makes a theoretical contribution by proposing the Machine Learning Adoption Framework (MLAF). In terms of practical implications, this study proposes an ML program specifically targeting the needs of farm owners in rural UAE. Policy-based implications are addressed by the findings aligning with the United Nations’ Sustainability Development Goals 9 (Industry, Innovation, and Infrastructure) and 11 (Sustainable Cities and Communities). Full article

Traffic accidents on urban roads are a major cause of death despite the development of traffic safety measures. However, the prediction of casualties in urban road traffic accidents has not been deeply explored in previous research. Effective forecasting methods for the casualties of traffic accidents can improve the manner of traffic accident warnings, further avoiding unnecessary loss. This paper provides a practicable model for traffic forecast problems, in which ten variables, including time characteristics, weather factors, accident types, collision characteristics, and road environment conditions, were selected as independent factors. A mixed-support vector machine (SVM) with a genetic algorithm (GA), sparrow search algorithm (SSA), grey wolf optimizer algorithm (GWO) and particle swarm optimization algorithm (PSO) separately are proposed to predict the casualties of collisions. Grounded on 4285 valid urban road traffic collisions, the computing results show that the SSA-SVM performs effectively in the casualties forecast compared with the GWO-SVM, GA-SVM and PSO-SVM. Full article

In the process of sustainable transformation, resource-based cities (RBCs) in Heilongjiang are in a dilemma. Resilience is a key capability to help RBCs deepen sustainable development, adapt to shocks, and exit the transformation dilemma. This study aims to clarify the resilience measurements and dynamics of RBCs and propose targeted resilience enhancement strategies. First, we construct a resilience indicator system based on the urban complex adaptive system (CAS) and use principal component analysis (PCA) to specify indicator weights to obtain the resilience values of RBCs in Heilongjiang Province during 2010–2019, then use cluster analysis to classify five resilience grades. Second, we identify and analyze the resilience dynamics of RBCs in Heilongjiang Province from 2010–2019 based on the adaptive cycle framework. The results indicate that the overall resilience dynamics of RBCs have exhibited an upward trend over the past decade, but there are clear variations in the level of resilience values and dynamics between the different types of RBCs. The petroleum-based city has the highest level of resilience, is less affected by shocks, and recovers quickly. Forest-based cities have a medium level of resilience and are able to recover from shocks, but they fail to improve and remain at a medium level for a long time. Coal-based cities have a low level of resilience and find it difficult to recover from shocks, but this has improved since 2017. Finally, we propose targeted resilience enhancement strategies for RBCs of different types and resilience levels in Heilongjiang Province to provide RBCs with directional guidance for overcoming the development dilemma through resilience measures. Full article

With the development of cities, the organization of jobs–housing space is becoming more complex, and the rapid, effective identification of both residences and workplaces is crucial to sustainable urban development. The long time series of online car-hailing data conveys a large amount of activity trajectory information about urban populations, which can represent the social functions of urban areas, including workplaces and residences. This paper constructs a jobs–housing site identification model based on human activity characteristics. This model uses a time series dataset of online car hailing that characterizes the changes in regional passenger flow and implements the similarity measure and semi-supervised learning of time series to determine the classification of urban areas. Then, the jobs–housing factor method is introduced to extract the jobs–housing characteristics of different regions, which achieves the jobs–housing site identification. Finally, the empirical analysis of Chengdu city shows that the proposed model method can effectively mine the distribution of urban jobs–housing sites. The identification results are consistent with the actual situation, and the combination of the time series similarity and the jobs–housing feature variable improves the identification effect, providing a new way of thinking about urban jobs–housing space research. Full article

To obtain an accurate one-dimensional velocity model, we developed the EA_VELEST method based on the evolutionary algorithm and the VELEST program. This method can quickly generate a suitable 1D velocity model and finally input it into the 3D velocity inversion process using the TomoDD method. We adopt TomoDD methods to inverse the high-resolution three-dimension velocity structure and relative earthquake hypocenters for this sequence. This system processing flow was applied to the Sichuan Maerkang earthquake swarm in 2022. By collecting the seismic phase data of the Maerkang area between 1 January 2009 and 15 June 2022, we relocated the historical earthquakes in the area and obtained accurate 3D velocity imaging results. The relocated hypocenters reveal a SE-trending secondary fault, which is located ~5 km NW of the Songgang fault. In the first ten-hour of the sequence, events clearly down-dip migrated toward the SE direction. The inverted velocity structure indicates that the majority of earthquakes during the sequence occurred along the boundaries of the high and low-velocity zones or high and low-V_P/V_S anomalies. Especially both the two largest earthquakes, M_S 5.8 and M_S 6.0, occurred at the discontinuities of high and low-velocity zones. The EA_VELEST method proposed in this paper is a novel method that has played a very good enlightenment role in the optimization of the one-dimensional velocity model in geophysics and has certain reference significance. The 3D velocity results obtained in this paper and the analysis of tectonic significance provide a reference for the seismogenic environment of this Maerkang earthquake and the deep 3D velocity of the Ganzi block. Full article

The huge amount of daily generated data in smart cities has called for more effective data storage, processing, and analysis technologies. A significant part of this data are streaming data (i.e., time series data). Time series similarity or dissimilarity measuring represents an essential and critical task for several data mining and machine learning algorithms. Consequently, a similarity or distance measure that can extract the similarities and differences among the time series in a precise way can highly increase the efficiency of mining and learning processes. This paper proposes a novel elastic distance measure to measure how much a time series is dissimilar from another. The proposed measure is based on the Adaptive Simulated Annealing Representation (ASAR) approach and is called the Adaptive Simulated Annealing Representation Based Distance Measure (ASAR-Distance). ASAR-Distance adapts the ASAR approach to include more information about the time series shape by including additional information about the slopes of the local trends. This slope information, together with the magnitude information, is used to calculate the distance by a new definition that combines the Manhattan, Cosine, and Dynamic Time Warping distance measures. The experimental results have shown that the ASAR-Distance is able to overcome the limitations of handling the local time-shifting, reading the local trends information precisely, and the inherited high computational complexity of the traditional elastic distance measures. Full article

Geographic object flow is the reason behind the relationship of geographic units. There are interactions in the process of dynamic change of a geographic object flow, and its regularity, which can reflect the relationship or pattern of geographic units in a region. In this paper, an association rule mining method for the geographic object flow linkage process is studied from a geoeconomics perspective. Additionally, an association rule mining algorithm with hierarchical constraints is proposed. Data segmentation is performed according to the time series characteristics of geographic object flow data. The basic attributes for the association rule mining are determined based on the basic parameters of geographic object flows, and a database for the association rule mining is formed according to the characteristics of the hierarchical structure of the geographic object flows. Based on the obtained data, the association rule mining algorithm with hierarchical constraints obtained using a parent–child matrix is improved by adding the Apriori algorithm. With the Indo-Pacific region as an example, the trade flow association rules for 25 countries in the region from 2010 to 2021 are selected. In addition, a mathematical statistical analysis of the strongly associated mined trade flows and geoeconomic factors is conducted in terms of both a basic feature analysis of trade flow associations and a country-oriented trade flow association analysis by considering domain knowledge. The effectiveness of the method has been evaluated from various perspectives such as correlation analysis, mathematical statistics, and comparison with the findings of existing studies and proved the validity of the method. Full article

The total allowable catch system (TACs) is a basic, widely used system for maintaining marine fishery resources. The vessel monitoring system (VMS) provides a superior method to monitor fishing activities that serve TACs project management. However, few studies have been conducted on this topic. Here, an artificial neural network was used to identify vessel position states based on BeiDou VMS data and fishing logs of vessels under the TACs project for Acetes chinensis in the Yellow Sea in 2021. Furthermore, fishing behaviors and intensity were explored. The results showed significant differences in the speed of vessels in different states (p < 0.01). Casting occurred during the day, and the azimuth of fishing nets for shrimp ranged from 60 to 90° or 240 to 270°. The length of the fishing nets of each vessel was mostly between 3500 and 4500 m. In addition, the fishing efforts of the vessels showed an obvious aggregated distribution. The main area was at 120°04′–120°16′ E, 34°42′–34°46′ N, whereas fishing intensity ranged from 120,000 to 280,000 m²·h/km². Finally, this study provides a scientific basis for TACs project management and a VMS data mining and application expansion standard. Full article

As an important symbol and carrier of regional social and economic activities, population mobility is a vital force to promote the re-agglomeration and diffusion of social and economic factors. An accurate and timely grasp on the impact of the COVID-19 epidemic on population mobility between cities is of great significance for promoting epidemic prevention and control and economic and social development. This study proposes a theoretical framework for resilience assessment, using centrality and nodality, hierarchy and matching, cluster, transmission, and diversity to measure the impact of the COVID-19 epidemic on population mobility in the Beijing–Tianjin–Hebei (BTH) urban agglomeration in 2020–2022, based on the migration data of AutoNavi and social network analysis. The results show that the COVID-19 epidemic had different impacts on the population network resilience of the BTH urban agglomeration based on the scale and timing. During the full-scale outbreak of the epidemic, strict epidemic prevention and control measures were introduced. The measures, such as social distancing and city and road closure, significantly reduced population mobility in the BTH urban agglomeration, and population mobility between cities decreased sharply. The population mobility network’s cluster, transmission, and diversity decreased significantly, severely testing the network resilience. Due to the refinement of the epidemic control measures over time, when a single urban node was impacted, the urban node did not completely fail, and consequently it had little impact on the overall cluster, transmission, and diversity of the population mobility network. Urban nodes at different levels of the population mobility network were not equally affected by the COVID-19 epidemic. The findings can make references for the coordination of epidemic control measures and urban development. It also provides a new perspective for the study of network resilience, and provides scientific data support and a theoretical basis for improving the resilience of BTH urban agglomeration and promoting collaborative development. Full article

Understanding the spatial pattern of urban house prices and its association with the built environment is of great significance to housing policymaking and urban planning. However, many studies on the influencing factors of urban housing prices conduct qualitative analyses using statistical data and manual survey data. In addition, traditional housing price models are mostly linear models that cannot explain the distribution of housing prices in urban areas. In this paper, we propose using geographic big data and zonal nonlinear feature machine learning models to understand housing prices. First, the housing price influencing factor system is built based on the hedonic pricing model and geographic big data, and it includes commercial development, transportation, infrastructure, location, education, environment, and residents’ consumption level. Second, a spatial exploratory analysis framework for house price data was constructed using Moran’s I tools and geographic detectors. Finally, the XGBoost model is developed to assess the importance of the variables influencing housing prices, and the zonal nonlinear feature model is built to predict housing prices based on spatial exploration results. Taking Shenzhen as an example, this paper explored the distribution law of housing prices, analyzed the influencing factors of housing prices, and compared the different housing price models. The results show that the zonal nonlinear feature model has higher accuracy than the linear model and the global model. Full article

Above-ground biomass (AGB) is a key indicator for studying grassland productivity and evaluating carbon sequestration capacity; it is also a key area of interest in hyperspectral ecological remote sensing. In this study, we use data from a typical alpine meadow in the Qinghai–Tibet Plateau during the main growing season (July–September), compare the results of various feature selection algorithms to extract an optimal subset of spectral variables, and use machine learning methods and data mining techniques to build an AGB prediction model and realize the optimal inversion of above-ground grassland biomass. The results show that the Lasso and RFE_SVM band filtering machine learning models can effectively select the global optimal feature and improve the prediction effect of the model. The analysis also compares the support vector machine (SVM), least squares regression boosting (LSB), and Gaussian process regression (GPR) AGB inversion models; our findings show that the results of the three models are similar, with the GPR machine learning model achieving the best outcomes. In addition, through the analysis of different data combinations, it is found that the accuracy of AGB inversion can be significantly improved by combining the spectral characteristics with the growing season. Finally, by constructing a machine learning interpretable model to analyze the specific role of features, it was found that the same band plays different roles in different records, and the related results can provide a scientific basis for the research of grassland resource monitoring and estimation. Full article