Deep Learning in the Mapping of Agricultural Land Use Using Sentinel-2 Satellite Data

In this paper the author analyses agricultural land use changes in the urban shadow of the Sydney metropolitan region and clarifies their sustainability on a micro-scale using the example of Castlereagh area, Penrith City. Castlereagh area is situated around the western suburbs of Sydney city centre, and is characterised by competition between agricultural and urban land use. In this area, rural and agricultural land use has generally developed since the colonial period. Although definite changes from agricultural to urban land use are not apparent with the advancement of urbanization, some kinds of agricultural use have changed to others in terms of function and quality since the 1990s. This sustainability of agricultural land use changes based on land, climate, and historical conditions as a suitable region for agriculture, and accessibility to the urban market for agricultural products, and land use policy of city planning and land use zoning.In Castlereagh area dairy farming and sheep grazing have traditionally developed with advantageous land and climate conditions for grass production. In particular, suburban dairy farming was important for town milk production. Although there were a few trends of conversion from dairy farming to sheep grazing, because of a decreasing agricultural labour force, the framework of traditional pastoral farming still remained until the 1980s. Since the 1990s most aspects of pastoral farming have changed into horse raising, horticulture, and hobby farming with the enlargement of urban land use for residential and factory sites. Such farming has been most apparent among all kinds of land use in the 1990s.Under an environment of urban shadow, both horse raising and horticulture have developed due to their suitability for expanding urban land use and farmland subdivisions. Agricultural land use changes are supported by economic factors such as capital intensity and high profitability. On the other hand, hobby farming is less intensive and rather unprofitable, and is developed for the mental satisfaction of aged and the urban residents, rather than the advancement of urbanisation and land subdivision. Therefore, agricultural land use changes into hobby farming are supported by non-economic factors such as productive aging and mental satisfaction. On the whole, a series of agricultural land use changes are identified for their sustainability, and are supported by economic and non-economic factors. In particular, hobby farming plays an important role in holding back urban sprawl and maintaining agricultural land use.

Strategies that target food security issues through the preservation of agricultural land are presently a focal point at the global level, particularly strategies that prevent agricultural land loss (no net land take). On the other hand, conflicts over land use, as well as the high value of land in urban areas, challenge the development of sustainable agriculture. Starting from the broadly adopted premise that planning affects land use change, especially agricultural land change, and that the Spatial Plan of the Republic of Serbia directly affects land use on the strategic-developmental and general regulatory level, the authors analyse the framework of the physical, planning and institutional capacities for sustainable agriculture and agricultural land use in Serbia. In their results, the authors provide: (1) an evaluation of new sustainable approaches for agriculture and agricultural land use planning and (2) a systematization of planning solutions at the strategic-developmental and general regulatory level regarding agricultural land use planning in Serbia for the period 2021–2035.KeywordsSustainable agricultureSpatial planningAgricultural landLand use planningSerbia

The article considers regional problems of agricultural land use and possible solutions. Unfinished land transformations – land-share quasi-ownership that not allocated, incomplete real estate cadaster where half the information on the location of agricultural land plots is missing, loss of project agricultural land use and land management infrastructure, as well as the absence of policy on regional agriculture and rational agricultural land use led to the corresponding results.

Modelling scenarios to assess the effects of different agricultural management and land use options to reduce diffuse nitrogen pollution into the river Elbe

Objective The automation of brachytherapy is the direction of future development. This article retrospectively studied the application of deep learning in brachytherapy of cervical cancer and clarified the status quo of development. Method This survey reviewed the application of machine learning and deep learning in brachytherapy for cervical cancer in the past 10 years. The survey retrieved and reviewed electronic journal articles in scientific databases such as Google Scholar and IEEE. The three sets of keywords used 1) deep learning, brachytherapy, 2) machine learning, brachytherapy, 3) automation, brachytherapy. Results Through research on the application of deep learning in brachytherapy, it is found that the U-net model is basically based on convolutional neural networks or some attention mechanisms are added to it, and it is applied to brachytherapy of prostate or cervical cancer. The automatic segmentation and reconstruction of the mid-source applicator (interpolation needle), target area delineation, optimization in the treatment planning system and dose calculation have achieved good results, proving that deep learning can be applied to the clinical treatment of brachytherapy. Conclusion The research on the application of deep learning in brachytherapy confirmed that deep learning can effectively promote the development of brachytherapy.

The article describes the foreign experience of organizing the use of agricultural land. Agricultural land as an object of legal relations is a unique natural resource that is depleted when not properly used and requires high costs to restore their fertility. Therefore, legal support for the proper use of agricultural land is designed to take into account the existence of private and public interests in relation to such land, to ensure their balance. Legal provisions of agricultural land in the conditions of a moratorium on the application of certain norms of land legislation are provided. A comparative legal analysis of the tools used in Kazakhstan and abroad to ensure the proper use of agricultural land allows us to identify existing, but not used, legal mechanisms that ensure the preservation of the qualitative and quantitative state of these lands, and analyze the prospects for their introduction into domestic legislation. At the level of national legislation, the priority form of agricultural land management is defined - peasant or farm farming, the main requirement for its activities is compliance with environmental requirements when using land. Based on this, measures are being developed to support the agricultural producer and preserve the agricultural land behind him. Foreign experience shows that during the period of sustainable use of agricultural land, such legal instruments are very effective and allow us to determine the desire of farmers to provide an opportunity to conduct agriculture. It is achieved through state regulation of their use and turnover, aimed at redistribution to agricultural producers. Borrowed from the legal practice of foreign countries in ensuring the proper use of agricultural land. Of course, it is necessary to take into account the history of the development of land relations in rural areas, social features, and current economic conditions for the development of a legal system aimed at the effective use of agricultural land.Thus, foreign experience in regulating the use and turnover of agricultural land is largely taken into account in domestic legislation.

Deep learning practitioners are often interested in improving their model accuracy rather than the interpretability of their models. As a result, deep learning applications are inherently complex in their structures. They also need to continuously evolve in terms of code changes and model updates. Given these confounding factors, there is a great chance of violating the recommended programming practices by the developers in their deep learning applications. In particular, the code quality might be negatively affected due to their drive for the higher model performance. Unfortunately, the code quality of deep learning applications has rarely been studied to date. In this paper, we conduct an empirical study to investigate the distribution of code smells in deep learning applications. To this end, we perform a comparative analysis between deep learning and traditional open-source applications collected from GitHub. We have several major findings. First, long lambda expression, long ternary conditional expression, and complex container comprehension smells are frequently found in deep learning projects. That is, deep learning code involves more complex or longer expressions than the traditional code does. Second, the number of code smells increases across the releases of deep learning applications. Third, we found that there is a co-existence between code smells and software bugs in the studied deep learning code, which confirms our conjecture on the degraded code quality of deep learning applications.

The excessive expansion of urbanized areas has resulted in haphazard land utilization, immoderate consumption of superior agricultural land and water resources, significant fragmentation of agricultural landscape, and gradual deterioration of the agro-ecological environment. Combined, these factors cause poor land use efficiency. Under these circumstances, comprehensively assessing land use efficiency for urban agriculture is a key issue in land use research. Currently, evaluation methods for agricultural land use efficiency narrowly concentrate on aspects of economic input and output. However, urban agro-ecosystems can provide diverse economic, social, and ecological services and functions. In particular, the social and ecological services and functions originating from agricultural land, which have a higher value than economic services, play a significant role in ensuring regional social, ecological, and environmental security. However, recent research has rarely taken these benefits into consideration. Therefore, land use value has been greatly underestimated, which has resulted in mishandled and poor land use policies. In this study, we apply Landsat imagery and social and economic statistical data for the Xi’an metropolitan zone (XMZ) to investigate agricultural multi-functionality. We develop an evaluation framework for urban agricultural land use efficiency and identify agro-ecosystem services and functions as important outputs from agricultural land. The land use efficiency of urban agriculture is then evaluated using ecosystem services models, providing a mechanism for assessing spatial-temporal changes in land use efficiency in the XMZ from 1999 to 2015. Four important conclusions are reached from this analysis. First, the rapid urbanization and agricultural transformation from traditional cereal cultivation to modern urban agriculture has resulted in steadily increasing costs, outputs, and land use efficiency of urban agriculture. The total output value increased 41% and land use efficiency per hectare increased by 33.13% on average. Second, the spatial patterns of comprehensive output and land use efficiency were dominated by economic outputs from agricultural land. Areas near cities, which are dominated by orchard and arable land, provide more economic functions. These areas support and regulate services due to the transformation from extensive cereal production to intensive modern urban agriculture; therefore, they have higher output value and land use efficiency. In contrast, areas distant from cities, towns, and high traffic roads, namely, remote rural areas, provide more support and regulating services, but have relatively lower economic function due to inaccessibility to urban markets and slow agricultural transformation. Therefore, these areas have lower output value and land use efficiency. The spatial change in agricultural output and land use efficiency in urban areas is strongly dependent on the degree of urbanization and agricultural transformation. Third, the total output value and land use efficiency of urban agriculture measured with our approach are much higher than evaluations using traditional methods. However, the spatial patterns measured using the two approaches are in agreement. The evaluation framework integrates ecological services and economic and social functions into a comprehensive output from agricultural land. This approach is more methodical and accurate for evaluating the comprehensive efficiency of land use based on quantities and spatial scale because they are at the pixel scale. Finally, the evaluation results have important implications for enhancing current agricultural subsidies and even implementing ecological payment policies in China. Most importantly, they can be directly applied to agricultural transformation regulations, decision- making, and guidance for rational land utilization.

This review paper investigates applications of machine learning and deep learning in trading, with a particular emphasis on recent advances in deep learning. It provides an overview of algorithms, including support vector machines (SVMs), random forests, deep neural networks (DNNs), long short-term memory networks (LSTM networks), and deep reinforcement learning (DRL). Findings show that while machine learning and deep learning models were able to surpass traditional strategies in general in terms of profitability, they were also better at risk management. However, despite their performances showing superiority, their performances varied significantly under different market conditions, including markets during periods of high and low volatility. In particular, LSTM networks and random forests can generate substantial returns, higher Sharpe ratios, and lower drawdowns compared to the benchmarks, whereas DNNs struggled during highly volatile periods, as reflected in the returns in the periods. Moreover, the improved DRL agent TradeNet-CR can manage risk significantly better than another, despite not surpassing the original TradeNet-CR model.

The extent of anthropogenic land use in watersheds determines the amount of pollutants discharged to streams. This indirectly and directly affects stream water quality and biological health. Most studies have therefore focused on ways to reduce non-point pollution sources to streams from the surrounding land use in watersheds. However, the mechanistic pathways between land use and the deterioration of stream water quality and biological assemblages remain unclear. This study estimated a structural equation model (SEM) representing the impact of agricultural and urban land use on water quality and the benthic macroinvertebrate index (BMI) using IBM AMOS in the Nam-Han river systems, South Korea. The estimated SEM showed that the percent of urban and agricultural land in the watersheds significantly affected both the water quality and the BMI of the streams. Specifically, a higher percent of urban land use had directly increased the biochemical oxygen demand (BOD) and total phosphorus (TP), and deteriorated the BMI of streams. Similarly, higher proportions of agricultural land use had also directly increased the BOD, total nitrogen (TN), and total phosphorus (TP) concentrations, and lowered the BMI of streams. In addition, it was observed that the percent of urban and agricultural land use had indirectly deteriorated the BMI through increased BOD. However, we were not able to observe any significant indirect effect of the percent of urban and agricultural land use through increased nutrients including TN and TP. These results indicate that increased urban and agricultural land use in the watersheds had directly and indirectly affected the physicochemical characteristics and benthic macroinvertebrate communities in streams. Our findings emphasize the need to develop more elaborate environmental management and restoration strategies to improve the water quality and biological status of streams.

Scientifically characterizing the spatial-temporal distribution characteristics of agricultural land use intensity and analyzing its driving factors are of great significance to the formulation of relevant agricultural land use intensity management policies, the realization of food safety and health, and the achievement of sustainable development goals. Taking Hubei Province as an example, and taking counties as the basic evaluation unit, this paper establishes an agricultural land use intensity evaluation system, explores the spatial autocorrelation of agricultural land use intensity in each county and analyzes the driving factors of agricultural land use intensity. The results show that the agricultural land use intensity in Hubei Province increased as a whole from 2000 to 2016, and the spatial agglomeration about the agricultural land use intensity in Hubei Province experienced a process of continuous growth and a fluctuating decline; the maximum of the Global Moran’s I was 0.430174 (in 2007) and the minimum was 0.148651 (in 2001). In terms of Local Moran’s I, H-H agglomeration units were mainly concentrated in two regions: One comprising the cities of Huanggang, Huangshi and Ezhou, and the other the cities of Xiangyang and Suizhou; the phenomenon is particularly obvious after 2005. On the other hand, factors such as the multiple cropping index (MCI) that reflect farmers’ willingness to engage in agricultural production have a great impact on agricultural land use intensity, the influence of the structure of the industry on agricultural land use intensity varies with the degree of influence of different industries on farmers’ income, and agricultural fiscal expenditure (AFE) has not effectively promoted the intensification of agricultural land use. The present research has important significance for enhancing insights into the sustainable improvement of agricultural land use intensity and for realizing risk control of agricultural land use and development.

The rapid development of Internet technology has made the whole society enter the era of big data. In recent years, the development trend of artificial intelligence and machine learning has also risen sharply. Informatization has become an important feature of the current era. As an indispensable common information carrier, images not only facilitate people’s communication, but also promote the development of deep learning processing image technology. Based on this, this paper analyzes the application of computer deep learning in image processing. Firstly, the deep learning is summarized, its concept and origin are briefly introduced, and then the technical classification, development process and processing purpose of image processing are expounded. Finally, the application of computer deep learning in four aspects is analyzed in detail in image recognition, image denoising, image classification and image enhancement, and it has certain significance for promoting the research and application of deep learning.

This study examines the links between agricultural and arable land use, access to electricity, economic growth, and demographic trends in several global regions, including sub-Saharan Africa, South Asia, East Asia and the Pacific, Europe and Central Asia, Central Europe and the Baltic States, Latin America and the Caribbean, and the Middle East and North Africa. The study hypothesizes that access to electricity moderates the relationship between agricultural land use, economic growth, and demographic trends, with regional disparities driven by differences in initial conditions such as infrastructure development and population dynamics. Using data from 2000 to 2022 from the World Bank database and Jamovi software, the analysis employs descriptive statistics, correlation, regression, moderation analysis, and Analysis of Variance (ANOVA) to explore regional disparities and identify challenges and opportunities for sustainable development. The results reveal significant regional disparities in electricity access, with regions such as Eastern and Southern Africa (31.8%) and sub-Saharan Africa (36.9%) facing significant electrification challenges compared to the near-universal access in Europe and Central Asia. Agricultural land use is a key determinant of economic stability, with South Asia having the highest percentage of agricultural land (56.7%), a pattern consistent with its agrarian economy. In contrast, the Middle East and North Africa faces significant constraints due to limited arable land (4.75%) and environmental challenges. The study also finds that regions such as Central Europe and the Baltics and East Asia and the Pacific have advanced agricultural practices and higher rates of urbanization, with less reliance on agriculture for economic stability. In addition, population growth shows a strong negative correlation with access to electricity (r = -0.834, p < 0.001), reflecting the demographic transition in developed countries where improvements in infrastructure coincide with lower fertility rates. Moderation analysis shows that in regions with low electricity access, such as sub-Saharan Africa, rapid population growth negatively affects GDP growth, but this effect is moderated by improvements in electricity access. Based on these findings, the study offers targeted recommendations for improving infrastructure, promoting sustainable agriculture, investing in human capital, and advancing inclusive urbanization strategies. These findings provide actionable guidance for policymakers seeking to address infrastructure deficits, reduce socioeconomic disparities, and overcome environmental constraints to achieve sustainable global development.

The study aims to identify some factors affecting agricultural land use management and propose solutions to improve it in Lang Son province. Secondary data were collected from agencies related to agricultural land use management. Primary data were collected through a direct survey of 250 officials and civil servants implementing agricultural land use management and through 2 steps. Step 1 identifies factors that may influence agricultural land use management. Step 2 collects opinions on the level of influence of the factors identified in Step 1. The hypothetical model of factors affecting land use management has 10 independent variables and 01 dependent variable, and they were evaluated through the testing criteria using SPSS20.0 software. Agricultural land use management is influenced by 28 factors belonging to 10 factor groups, with impact rates ranging from 3.65% to 23.57%. The group of factors of inspection, examination, and sanctioning of land related administrative violations has the most impact, and the group of factors of infrastructure conditions has the least impact on land use management. Proposed solutions include strengthening inspection, examination, and strict penalties for land violations; Completing and properly resolving complaints, denunciations, and land disputes; improving human resources; Organizing and implementing well land use management, etc.

At present, the sustainable development of rural areas is one of the main goals of modern state agrarian policy. The system of modern agricultural land use should be formed under the influence of economic, social, legal, environmental and natural conditions of the territory. The authors of modern scientific publications on the sustainability of agricultural land use often consider the concept of sustainability from an agroecological point of view, as maintaining fertility and preventing negative processes. Agroecological capacity is the most important factor affecting agricultural land use efficiency. The paper considers the role of agroecological potential in the system of sustainable agricultural land use. A survey of domestic sources on the importance of agroecological and bioclimatic potential in enhancing the sustainability of agricultural land use was conducted. The concept of agroecological potential of agricultural land use was clarified. The object of the study is the agricultural land use in Volokolamsk district of Moscow region. A comprehensive analysis of financial results of agricultural enterprises and organizations in Moscow region was carried out, which showed low profitability of agricultural land use. The methodology and calculation of agroecological potential of agricultural land use in Volokolamsk district of Moscow region were considered. The measures to increase the possibility of using the generalized assessment of bioclimatic and agroecological resources of Volokolamsk district of Moscow region were proposed and the efficiency assessment on main crops over the past 15 years and comparison with the values of bioclimatic potential of agroecological potential for agricultural land management purposes was performed. The modern principles of sustainable agricultural land use require the placement and specialization of agricultural production in accordance with the agroecological conditions of the territories.