Evaluation method for ecology-agriculture-urban spaces based on deep learning.

With the increasing global population and escalating ecological and farmland degradation, challenges to the environment and livelihoods have become prominent. Coordinating urban development, food security, and ecological conservation is crucial for fostering sustainable development. This study focuses on assessing the "Ecology-Agriculture-Urban" (E-A-U) space in Yulin City, China, as a representative case. Following the framework proposed by Chinese named "environmental capacity and national space development suitability evaluation" (hereinafter referred to as "Double Evaluation"), we developed a Self-Attention Residual Neural Network (SARes-NET) model to assess the E-U-A space. Spatially, the northwest region is dominated by agriculture, while the southeast is characterized by urban and ecological areas, aligning with regional development patterns. Comparative validations with five other models, including Logistic Regression (LR), Naive Bayes (NB), Gradient Boosting Decision Trees (GBDT), Random Forest (RF) and Artificial Neural Network (ANN), reveal that the SARes-NET model exhibits superior simulation performance, highlighting it's ability to capture intricate non-linear relationships and reduce human errors in data processing. This study establishes deep learning-guided E-A-U spatial evaluation as an innovative approach for national spatial planning, holding broader implications for national-level territorial assessments.

Evolution characteristics and multi-scenario prediction of habitat quality in Yulin City based on PLUS and InVEST models.

As a major energy city in China, Yulin City has faced huge challenges to the ecological environment with its rapid economic development and rapid urbanization. Therefore, it is of great significance to study the impact of land use changes on habitat quality. Based on three periods of land use data in Yulin City in 1995, 2005 and 2015, the PLUS model was used to simulate the land use changes in 2015. The measured kappa coefficient was 0.8859, which met the simulation accuracy requirements. By setting development zone boundaries and adjusting parameters, three progressive scenarios are designed to predict the spatial distribution of land use in Yulin City in 2035. The InVEST model was used to analyze the spatiotemporal evolution of Yulin City's habitat quality in the past 20 years and evaluate the distribution of Yulin City's habitat quality under three scenarios after 20 years. The results are as follows: (1) During the study period, construction land in Yulin City expanded rapidly, with an area increase of 380.87 km2 in 20 years, and ecological land gradually shrank. (2) The land use simulation results of Yulin City under various scenarios in 2035 show that future land use changes in Yulin City will mainly be concentrated in the central and western regions. (3) During the study period, the habitat quality of Yulin City was at a medium level and the overall habitat quality showed a downward trend. Spatially, the degree of habitat quality degradation in Yulin City showed a characteristic of gradually decreasing from West to East. (4) By 2035, under the scenario of suitable urban economic development, Yulin City's habitat quality has been improved to a certain extent, which not only protects ecological security but also meets the demand for construction land for urban development. The results of this study help the government better understand the evolution of land use and habitat quality in Yulin City in the past 20 years, and provide theoretical support and reference for the formulation of Yulin City's ecological environment protection policies and the implementation of ecological protection work under the current land spatial planning.

Comprehensive evaluation of the underground space resources in Xianyang city.

With the rapid development of urbanization and the sharp increase in population, urban land is becoming increasingly scarce. The efficient and reasonable development of the underground space is a crucial way to solve the problem of urban diseases, and comprehensive evaluation of urban underground space resources is an important basic task to achieve reasonable planning of the underground space. Adopting Xianyang city as an example, in this paper, we comprehensively evaluated the underground space resources in the main urban area and established evaluation models for the amount of resources available for development, development difficulty, potential value, and comprehensive quality of the underground space. Evaluation indicators, including urban environmental constraints, geological conditions, socioeconomic conditions and many other factors, were determined. With the use of the method of item-by-item elimination of restrictive elements and the analytic hierarchy process for determining the weight of each evaluation index, GIS technology was used to calculate and evaluate the underground space resources (0-30 m) in the main urban area of Xianyang city that could be reasonably developed, as well as the corresponding development difficulty and potential value, and we obtained the underground space that could be reasonably developed under different types of land use in the main urban area of Xianyang city on the basis of the resource quantity and comprehensive quality evaluation results. The results showed that in terms of quantity, the amount of underground space available for development in the main urban area of Xianyang city accounts for approximately 25.11% of the total development amount, and the underground space that could be developed and utilized is approximately 82.3 km2. The underground space resources that could be developed within a 30 m depth interval in the main urban area reached 2.465 billion m3, accounting for approximately 79.5% of the total shallow underground space resources, and the potential for development and utilization is enormous. In terms of the comprehensive quality, the highest comprehensive quality level of shallow underground resources is located in the core areas along Renmin Road, Weiyang Road, and Century Avenue, with an area of 21.52 km2, and the highest comprehensive quality level of subshallow underground resources is located along Renmin Road and Weiyang Road, with an area of 4.37 km2. The evaluation results could provide high reference value for urban development planning and underground space development and utilization in Xianyang.

Image-Processing-Based Subway Tunnel Crack Detection System.

With the increase in urban rail transit construction, instances of tunnel disease are on the rise, and cracks have become the focus of tunnel maintenance and management. Therefore, it is essential to carry out crack detection in a timely and efficient manner to not only prolong the service life of the tunnel but also reduce the incidence of accidents. In this paper, the design and structure of a tunnel crack detection system are analyzed. On this basis, this paper proposes a new method for crack identification and feature detection using image processing technology. This method fully considers the characteristics of tunnel images and the combination of these characteristics with deep learning, while a deep convolutional network (Single-Shot MultiBox Detector (SSD)) is proposed based on deep learning for object detection in complex images. The experimental results show that the test set accuracy and training set accuracy of the support vector machine (SVM) in the classification comparison test are up to 88% and 87.8%, respectively; while the test accuracy of Alexnet's deep convolutional neural network-based classification and identification is up to 96.7%, and the training set accuracy is up to 97.5%. It can be seen that this deep convolutional network recognition algorithm based on deep learning and image processing is better and more suitable for the detection of cracks in subway tunnels.

A hybrid ensemble method based on double disturbance for classifying microarray data.

Microarray data has small samples and high dimension, and it contains a significant amount of irrelevant and redundant genes. This paper proposes a hybrid ensemble method based on double disturbance to improve classification performance. Firstly, original genes are ranked through reliefF algorithm and part of the genes are selected from the original genes set, and then a new training set is generated from the original training set according to the previously selected genes. Secondly, D bootstrap training subsets are produced from the previously generated training set by bootstrap technology. Thirdly, an attribute reduction method based on neighborhood mutual information with a different radius is used to reduce genes on each bootstrap training subset to produce new training subsets. Each new training subset is applied to train a base classifier. Finally, a part of the base classifiers are selected based on the teaching-learning-based optimization to build an ensemble by weighted voting. Experimental results on six benchmark cancer microarray datasets showed proposed method decreased ensemble size and obtained higher classification performance compared with Bagging, AdaBoost, and Random Forest.