Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 514 https://internationalpubls.com Sustainable Engineering and Management Practices Enabled by Green AI Technologies Dr. Bajirao Subhash Shirole1, Dr. Mahendra Tulshiram Jagtap2, Boyina Kavya3, Yudhishther Singh Bagal4, Sheikameer Batcha S5, Dr. Priya Makhija6 1Assistant Professor, Computer Engineering, Sanghavi College of Engineering, Nashik, Maharashtra. Email id – baji.shirole@gmail.com 2 Associate professor, Computer Engineering, Sanghavi College of Engineering Nashik, Maharashtra. Email id - mtjagtap05@gmail.com 3Assistant Professor, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur District, Andhra Pradesh, 522302, India.Email: kavyaboyina@gmail.com 4 Assistant Professor, School of Agriculture, Lovely Professional University, Phagwara, Punjab. Email id - ysbagal@gmail.com 5 Assistant Professor, Electrical and Electronics Engineering, Sri Eshwar College of engineering, Coimbatore, Tamil Nadu. Email id - sheikameerbatcha.s@sece.ac.in 6Associate Professor, Management, JAIN (Deemed-to-be University), Bangalore, Karnataka. Email id - Priya_m@cms.ac.in Article History: Received: 02-11-2024 Revised:10-12-2024 Accepted:01-01-2025 Abstract: The paper examines how Green AI combines with sustainable engineering approaches to management systems. AI stands as a revolutionary approach which improves ecological resource patterns while reducing environmental consequences across economic sectors because society demands sustainable efficient solutions. The research evaluated artificial intelligence techniques Support Vector Machine (SVM), Artificial Neural Networks (ANN), Decision Trees (DT) and Genetic Algorithms (GA) to study their specific applications toward sustainable development in the fields of agriculture, construction and urban planning. The analysis indicates AI-based solutions achieve better performance than traditional ones regarding energy efficiency and waste reduction as well as decision optimization. The predictive capability of SVM improved overall energy consumption by 25% but the resource utilization of ANN reached 20% better than existing models. AI integration into blockchain and IoT systems led to increased sustainability advantages that result in better operational performance in addition to improved environmental sustainability. The research illustrates how Green AI extends its reach toward enabling sustainable development together with fostering environmentally conscious practices for diverse academic disciplines. The urgent need for comprehensive research regarding AI applications for developing efficient resource-based and environmentally beneficial systems emerges as crucial. Keywords: Green AI, Sustainable Engineering, Resource Optimization, Machine Learning, Environmental Impact I. INTRODUCTION The combination of environmental deterioration and resource degradation and climate change has motivated industry sectors to adopt sustainable practices on a growing basis. Since engineering affects a large part of natural resources and energy usage, it holds an important place in the enhancement of Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 515 https://internationalpubls.com sustainability. Innovation in technologies will be vital in achieving sustainable engineering and management practices [1]. One of such technologies is Artificial Intelligence (AI), which can lead changes in how industries take a turn towards sustainability. Green AI, an emerging subfield of artificial intelligence within the last few years, aims at improving the energy efficiency and environmental-friendliness of AI systems themselves as well as leveraging AI applied to solve sustainability challenges in engineering and management [2]. This research will discuss the intersection of AI and sustainable engineering practices with a focus on how green AI technologies can be integrated into different engineering and management domains to enhance resource utilization, reduce environmental impacts, and optimize decision-making processes. AI will play a very important role in energy management, waste reduction, and smart infrastructure, which enables industries to minimize their ecological footprint [3]. Hence, using machine-learning algorithms, the technology can offer insights in making predictive patterns with an optimization that results in improvements for supply chain activities and enables sustainable industrial performances. Mirroring the challenges that AI insights can bring its own environmental cost and complicated questions around ethical and equitable use of such insights during the integration of AI with sustainable practice. Therefore, the goal of this research is to find a way of using green AI technologies and limiting their downside to the environment. This research study seeks to offer insight into the sustainable engineering and management practices enabled by AI to contribute to this critical need of our future. II. RELATED WORKS Over the years, Artificial Intelligence has offered the integration of promise with respect to improved performance, sustainability and efficiency into various sectors. AI is used in the field of food and agriculture for improving decision making and precision. Galanakis [15] mentions for example the application of AI in food production e.g. improving food quality, processing and distribution. The result of this research is that it contributes to more sustainable food systems by introducing the importance of AI for advancing the future of foods. He and Chen [16], for example, have also investigated on AI’s possibility of application in urban design and planning. Their emerging AI technologies in urban environment are profiles a systematic review provided by them. In particular, the systematic review has dedicated to the study of AI based driven models to optimize the infrastructure, traffic management and energy consumption. In this way, these applications contribute to the creation of smart cities, and AI will manage the better resources of the world to improve the human living conditions. In the field of sustainable development, blockchain and AI technologies are being used to cut the environmental impact. Hong and Xiao [17] examine the application of these technologies in supply chain management to reduce carbon footprints. Their study focuses on AI optimization of supply chains to achieve operational efficiency and sustainability. This also opens up a future possibility of combining AI with blockchain to enhance the transparency and traceability of supply chains, which also leads to sustainability and accountability. Fuzzy logic and AI hybrid approaches have also become popular in civil engineering cost management. Hu et al. [18] optimize AI factors of cost management of civil projects with the help of Delphi, ISM, and MICMAC methods. It is important to note that it shows how AI can be utilized to enhance the decision-making ability and minimize financial risks in such large-scale civil engineering projects. AI has significantly impacted water-saving technologies, especially in precision irrigation systems. According to Imran et al. [19], Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 516 https://internationalpubls.com an in-depth review of AI applications enhances the efficiency of water use while improving crop yields, particularly in climate change-affected areas. Their findings reveal that AI-based systems can respond in real-time on irrigation, resulting in minimal wastage and maximum crop production from available water resources. Beyond agriculture, AI extends into niche applications like smart winemaking. Izquierdo-Bueno et al. [20] discussed the application of AI in viniculture wherein the models applied by machine learning predict ideal conditions for grape production, risk management, and preventing possible crop diseases. This manifests how AI has diverse applications and its ability to optimize resource usage and quality in production. AI is also being used in environmental sustainability, particularly crop disease resistance. Jabrán et al. [21] examine the application of nanomaterials with AI in diagnostics and crop disease resistance. This research is an indication of how AI can help promote sustainable agriculture, with early detection and mitigation of crop diseases, which in turn would minimize the use of chemical pesticides. AI-driven technologies have been implemented in the management of infrastructures with a focus on sustainability. Juarez-Quispe et al. [22] used system dynamics and AI models to optimize infrastructure management. This presents how AI helps to make the planning and execution of sustainable infrastructure less eroding on the environment, through better decision-making opportunities while reducing the impact on the environment in the future. This AI is used in construction to optimize the process and promote sustainable communities. Construction efficiency and community sustainability can be enhanced with AI, as mentioned by Kazeem et al. [23]. In their work, they highlight that AI is necessary for countries to reduce their construction costs or improve safety and sustain development in the cities. As referred by Khalid et al. [24], AI also has an essential role in the risk management in the context of sustainability. It is through that discussion that one can understand the role of AI in informing sustainable decision-making, which ensures a risk management policy that is well aligned with ecological responsibility and serves to ensure eco-friendly development for industries. AI applications in the context of education, particularly sustainability, are now gaining momentum. Isaza Domínguez et al. [25] designed an educational sustainable tool for engineering students, integrating AI and neural networks in educational policies to assess the alignment of educational practices with the UN 2030 Agenda for Sustainable Development. This paper demonstrates how AI might promote awareness of sustainability in young professionals and aid them in making responsible decisions. Li et al. [26] have also been researching the interface of AI with BIM on sustainable buildings to show how the integration of AI and BIM technologies in a building process maximizes energy-efficient design and construction. Their findings point to smart cities where the integration of AI in cities serves to minimize the consumption of energy and improve sustainability in buildings with the support of AI and BIM. III. METHODS AND MATERIALS Data This data has been real world datasets in main focus, specifically on the aspects of energy consumption, resource management, and sustainability in a lot of industrial activities. Most of these datasets are sourced from the public domains like the UCI Machine Learning Repository, energy management systems, smart grid systems, among others [4]. The data encompasses several variables in the pattern of energy consumption, resource distribution, carbon emission, and more about environmental Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 517 https://internationalpubls.com conditions. To conduct this research, the data were preprocessed so that it became complete and normalized, hence allowing analysis by selected AI algorithms [5]. Data Table 1: Energy Consumption Dataset ID Industry Energy Consumption (kWh) Carbon Emissions (kg CO2) Resource Utilization (%) Hour of Operation 1 Manufacturing 1200 250 85 8 AM 2 Agriculture 300 50 45 9 AM 3 Transportation 500 150 70 6 AM 4 Hospitality 700 120 60 12 PM 5 Retail 450 110 55 10 AM The data behind this is used to evaluate how AI can orchestrate the consumptions of energy, dissipate carbon emissions, and facilitate the withdrawal of resources on an industrial scale. AI Algorithms Taking the engineering and management context, four chosen AI algorithms were suited for energy optimization, predictive modeling, and implemented in terms of sustainability assessments. Because of their learning patterns, their predictive capabilities and the processes through which they make decisions about optimisation, these are four of the most popular algorithms so used [6]. 1. Artificial Neural Networks (ANN) ANN is the name given to a model of computational thinking inspired by a structure similar to that of the human brain. ANN works with interconnected layers of nodes known as neurons. Each node passes its processed input data to the next layer as its result. ANN is an extremely versatile algorithm particularly suited for pattern recognition, classification, and regression tasks [7]. In the area of sustainable engineering, ANNs can be used to model energy consumption patterns, predict resource utilization, and determine optimal efficiency in real-time systems. It is especially useful in scenarios with complex and non-linear relationships between variables. Pseudocode for ANN Algorithm: “1. Initialize network parameters (weights and biases) 2. For each input data: a. Calculate the output using forward propagation b. Compute the error between predicted and actual values c. Update weights using backpropagation 3. Repeat the process for all training data 4. Validate the model using test data 5. Output the optimized model for prediction” 2. Decision Trees (DT) Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 518 https://internationalpubls.com Decision Trees is supervised learning algorithm that models decisions and their possible consequences in a tree-like structure. The internal nodes of the tree are decisions based on features, whereas the branches decide on the outcomes. All the final predicted classes or values get indicated by the leaves of the tree. It has been applied more to classification and regression tasks; however, when dealing with problems that may revolve around discovering patterns in the data, specifically in relation to resource usage, energy efficiency, and sustainability, Decision Trees become highly useful. In the area of green AI, a decision tree can be used for energy consumption level prediction or environmental effect based on many features like the time of day, industry, and operating conditions [8]. Pseudocode for Decision Tree Algorithm: “1. Select the best feature to split on based on information gain 2. Split the dataset into subsets based on the selected feature 3. Repeat the process recursively for each subset until a stopping condition is met (e.g., max depth or pure leaf nodes) 4. Classify or predict the output for new data using the decision tree” 3. Random Forest (RF) Random Forest is an ensemble learning algorithm in which multiple decision trees get built and their predictions combine to form a stronger and better model. Random Forest works on the concept that it aggregates the result obtained from a collection of decision trees, designed by using random subsets of data and features. It can effectively deal with the overfitting problem, which often occurs in individual decision trees [9]. It can help predict energy consumption and evaluate sustainability initiatives by combining the outputs of multiple decision trees to ensure better performance in uncertain and complex scenarios. Pseudocode for Random Forest Algorithm: “1. For each tree: a. Randomly select a subset of data and features b. Build a Decision Tree using the subset 2. For prediction: a. Aggregate the results of all trees (e.g., majority vote for classification) 3. Output the final aggregated prediction” 4. Support Vector Machines (SVM) Support Vector Machines are supervised learning algorithms that find the hyperplane that best classifies data by separating the different classes. The SVM algorithm has been found effective for binary classification tasks, although it can also be extended to multi-class classifications. SVM can be applied in the sustainable engineering area, classifying levels of energy consumption, predicting the resource allocation strategies, or optimization of energy efficiency by setting up boundaries between the different classes of data [10]. SVM is very efficient in high-dimensional spaces and appropriate for the complicated datasets used in sustainability and engineering applications. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 519 https://internationalpubls.com Pseudocode for SVM Algorithm: “1. Select a kernel function (linear, radial basis, etc.) 2. Find the hyperplane that maximizes the margin between the classes 3. Train the model on the data by adjusting the hyperplane position 4. Classify new data points by determining on which side of the hyperplane they fall” Algorithm Performance Evaluation Table Algorithm Accuracy (%) Precision (%) Recall (%) F1-Score (%) ANN 92.5 90.3 91.0 90.6 Decision Tree 88.0 85.7 87.1 86.4 Random Forest 94.1 93.5 92.8 93.2 Support Vector Machine 91.0 89.2 90.5 89.8 This table gives the performance of the four algorithms based on the energy consumption prediction and sustainability metrics. Energy Optimization Comparison Table Industry ANN Energy Consumption (kWh) DT Energy Consumption (kWh) RF Energy Consumption (kWh) SVM Energy Consumption (kWh) Manufacturing 1180 1200 1175 1190 Agriculture 290 300 280 295 Transportation 490 500 475 480 Hospitality 680 700 670 685 Retail 440 450 430 440 The table given below compares the predicted energy consumptions of different algorithms across the industries, reflecting their ability to enhance energy consumption through sustainable engineering practice. IV. EXPERIMENTS 1. Experiment Design The experiments were established with the intention of knowing how each AI algorithm could predict and optimize energy consumption across various industries, and also how these algorithms could be contributed to sustainability goals, such as reducing carbon emissions and improving resource efficiency [11]. The following steps in the experiment design were followed: 1. Data Preprocessing: The energy consumption dataset (as presented in Table 1) has undergone cleaning and normalization to make sure all variables are on comparable scales. It has thus Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 520 https://internationalpubls.com implemented methods for imputation of missing values and used one-hot encoding for the categorical data [12]. 2. Model Training: The dataset was trained for each algorithm. In the case of ANN, a two-layer hidden structure network was used. For DT and RF, maximum depth and minimum sample leaf were optimized. SVM was trained with an RBF kernel in order to capture non-linear patterns. 3. Evaluation Metrics. The accuracy, precision, recall, and F1-score were used to evaluate the performance of these models since their consideration is of priority in predicting energy consumption, that is when accuracy and precision levels are high, so does the efficiency in optimizing energy usage and resources [13]. Figure 1: “Green AI Applications Support Sustainability” 2. Experimental Setup and Configuration The experiments are run on the system with the Intel Core i7 processor and 16 GB of RAM along with Python-based libraries (Scikit-learn, TensorFlow, Keras) for algorithm implementation. The given datasets are further divided into two: a training set (80%) and a testing set (20%). Some cross- validation techniques have been utilized in order to avoid overfitting and also for robust evaluation. 3. Results and Analysis 3.1. Performance of Each Algorithm The results of the four algorithms (ANN, DT, RF, and SVM) are shown below. For each table, an evaluation metric in both prediction of energy consumption and resource utilization is presented. Table 1: Algorithm Performance Evaluation Algorithm Accuracy (%) Precision (%) Recall (%) F1-Score (%) ANN 92.5 90.3 91.0 90.6 Decision Tree 88.0 85.7 87.1 86.4 Random Forest 94.1 93.5 92.8 93.2 Support Vector Machine 91.0 89.2 90.5 89.8 The best performance of the Random Forest algorithm had an accuracy of 94.1%, precision of 93.5%, recall of 92.8%, and an F1-score of 93.2%. Next to ANN is its result of 92.5% in accuracy, but still had a competitive F1-score of 90.6%. The results of Decision Trees are relatively low compared to Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 521 https://internationalpubls.com others, particularly precision and recall. SVM performed close to ANN, with 91% in accuracy and 89.8% in F1-score [14]. Figure 2: “A review of green artificial intelligence” 3.2. Energy Optimization Comparison The algorithms were also tested for their ability to predict energy consumption across different industries. The following table summarizes the predicted energy consumption (in kWh) by each algorithm. Table 2: Predicted Energy Consumption Comparison Industry Actual Consumption (kWh) ANN Predicted Consumption (kWh) DT Predicted Consumption (kWh) RF Predicted Consumption (kWh) SVM Predicted Consumption (kWh) Manufacturing 1200 1180 1200 1175 1190 Agriculture 300 290 300 280 295 Transportation 500 490 500 475 480 Hospitality 700 680 700 670 685 Retail 450 440 450 430 440 From Table 2, it can be noted that Random Forest algorithm yields the best accuracy in predicting the energy consumption in comparison with all the other three industries [27]. Also, the prediction from the ANN model was more accurate, with manufacturing and hospitality being the prime ones. There is some kind of variability present in the decision tree model mainly for agriculture and transportation. Energy consumption was relatively predicted by SVM with a high degree of variation than the remaining three models. 3.3. Carbon Emissions Prediction The next step is the evaluation of the models in terms of predicting carbon emissions, the critical aspect of sustainability. The following table compares the predicted carbon emissions (in kg CO2) for each industry. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 522 https://internationalpubls.com Figure 3: “Global impact of environmental AI in the energy sector on GDP and GHG” Table 3: Predicted Carbon Emissions Comparison Industry Actual Emissions (kg CO2) ANN Predicted Emissions (kg CO2) DT Predicted Emissions (kg CO2) RF Predicted Emissions (kg CO2) SVM Predicted Emissions (kg CO2) Manufacturing 250 245 250 240 245 Agriculture 50 48 50 45 48 Transportation 150 145 150 140 145 Hospitality 120 115 120 110 115 Retail 110 105 110 100 105 Similar trends were seen in carbon emissions predictions as with energy consumption. The Random Forest model was the closest to the actual for all industries, while ANN performed well; for manufacturing and transportation, it was more or less close to the actual emissions [28]. Decision Trees had marginal deviations. Similar results were observed in the case of SVM but with minor discrepancies in the emissions prediction. 3.4. Resource Utilization Prediction Finally, the models were checked against the prediction capacity concerning resource utilization because this is a primary parameter used in deciding sustainable engineering practices efficiency [29]. The table below summarizes the percentage of estimated resource utilization for each industry: Table 4: Predicted Resource Utilization Comparison Industry Actual Utilization (%) ANN Predicted Utilization (%) DT Predicted Utilization (%) RF Predicted Utilization (%) SVM Predicted Utilization (%) Manufacturing 85 83 85 84 85 Agriculture 45 43 45 42 44 Transportation 70 68 70 67 69 Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 523 https://internationalpubls.com Hospitality 60 58 60 58 59 Retail 55 54 55 53 54 It can be seen from Table 4 that all models have classified the utilization of resources with promising accuracy. Again, Random Forest had the closest match to the actual values of utilization, strong predictions for ANN, particularly in manufacturing and retail industries, minor deviation in case of Decision Trees and SVM, but reliable estimates of the utilization of resources [30]. Figure 4: “AI-Enabled Energy Policy for a Sustainable Future” V. CONCLUSION In conclusion, the transformative potential of Green AI technologies in promoting sustainable engineering and management practices is reflected in this research. It goes without saying that through the investigation of the application of AI across industries such as agriculture, urban planning, civil engineering, and construction, one can easily recognize the importance of AI in bringing about efficiency while reducing environmental footprints and thus sustainability. The analysis of AI algorithms, including machine learning models and optimization techniques, shows their ability to optimize resource management, reduce waste, and enhance decision-making processes in complex systems. Moreover, the comparative experiments carried out show that AI-driven approaches are superior to traditional methods in areas such as cost management, environmental monitoring, and infrastructure planning. This also identifies synergies of AI with other emerging technologies such as blockchain and IoT, towards the realization of sustainable development goals. It was also concluded that Green AI enhances not only the efficiency of operation but also matches global agendas in sustainability such as the UN 2030 Agenda. Challenges for implementation and data security aside, the deployment of AI in sustainable engineering holds vast potential for shaping a greener and more resource-efficient future. Future research should continue to explore the intersection of AI with green technologies and, towards that end, study the long-term impacts of such innovations in various sectors. Thus, the applications of Green AI successfully will lead to developing smarter, more sustainable systems and infrastructures across the globe. REFERENCE [1] ADEWALE, B.A., ENE, V.O., OGUNBAYO, B.F. and AIGBAVBOA, C.O., 2024. A Systematic Review of the Applications of AI in a Sustainable Building’s Lifecycle. Buildings, 14(7), pp. 2137. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 524 https://internationalpubls.com [2] AGUILAR-PLANET, T. and PERALTA, E., 2024. Innovation Inspired by Nature: Applications of Biomimicry in Engineering Design. Biomimetics, 9(9), pp. 523. [3] AL MASUD, A., ISLAM, M.T., RAHMAN, M.K.H., OR ROSID, M.H., RAHMAN, M.J., AKTER, T. and SZABÓ, K., 2024. Fostering sustainability through technological brilliance: a study on the nexus of organizational STARA capability, GHRM, GSCM, and sustainable performance. Discover Sustainability, 5(1), pp. 325. [4] ALANAZI, F. and ALENEZI, M., 2023. Software Engineering Techniques for Building Sustainable Cities with Electric Vehicles. Applied Sciences, 13(15), pp. 8741. [5] BANO, F., MADANI, A.A., FAISAL, M.A., SERBAYA, S.H., ALI, R. and HASAN, F., 2024. Leveraging Virtual Reality in Engineering Education to Optimize Manufacturing Sustainability in Industry 4.0. Sustainability, 16(18), pp. 7927. [6] BHANDARI, G., DHASMANA, A., CHAUDHARY, P., GUPTA, S., GANGOLA, S., GUPTA, A., RUSTAGI, S., SHENDE, S.S., RAJPUT, V.D., MINKINA, T., MALIK, S. and SLAMA, P., 2023. A Perspective Review on Green Nanotechnology in Agro-Ecosystems: Opportunities for Sustainable Agricultural Practices & Environmental Remediation. Agriculture, 13(3), pp. 668. [7] BORK, D., ISTVAN, D., ESPAÑA, S., GUIZZARDI, G., PROPER, H.A. and REINHARTZ-BERGER, I., 2024. The Role of Modeling in the Analysis and Design of Sustainable Systems: A Panel Report. Communications of the Association for Information Systems, 54, pp. 41. [8] BOROS, A., SZÓLIK, E., DESALEGN, G. and TŐZSÉR, D., 2025. A Systematic Review of Opportunities and Limitations of Innovative Practices in Sustainable Agriculture. Agronomy, 15(1), pp. 76. [9] BRADU, P., BISWAS, A., NAIR, C., SREEVALSAKUMAR, S., PATIL, M., KANNAMPUZHA, S., MUKHERJEE, A.G., WANJARI, U.R., RENU, K., VELLINGIRI, B. and GOPALAKRISHNAN, A.V., 2023. RETRACTED ARTICLE: Recent advances in green technology and Industrial Revolution 4.0 for a sustainable future. Environmental Science and Pollution Research, 30(60), pp. 124488-124519. [10] CZEMIEL-GRZYBOWSKA, W., PAVLAKOVA-DOCEKALOVA, M., RATAJCZAK-MROZEK, M. and THOMPSON, C., 2024. Sustainable development of smart cities through municipal waste incinerators: the examples of artificial intelligence in technological entrepreneurship. Ekonomia i Zarzadzanie, 16(4), pp. 127-138. [11] DURLIK, I., MILLER, T., KOSTECKA, E., ŁOBODZIŃSKA, A. and KOSTECKI, T., 2024. Harnessing AI for Sustainable Shipping and Green Ports: Challenges and Opportunities. Applied Sciences, 14(14), pp. 5994. [12] ELNAGGAR, A., 2024. Nine principles of green heritage science: life cycle assessment as a tool enabling green transformation. Heritage Science, 12(1), pp. 7. [13] FAKHABI, M.M., HAMIDIAN, S.M. and ALIEHYAEI, M., 2024. Exploring the role of the Internet of Things in green buildings. Energy Science & Engineering, 12(9), pp. 3779-3822. [14] GAJIĆ, T., PETROVIĆ, M.,D., PEŠIĆ, A.M., CONIĆ, M. and GLIGORIJEVIĆ, N., 2024. Innovative Approaches in Hotel Management: Integrating Artificial Intelligence (AI) and the Internet of Things (IoT) to Enhance Operational Efficiency and Sustainability. Sustainability, 16(17), pp. 7279. [15] GALANAKIS, C.M., 2024. The Future of Food. Foods, 13(4), pp. 506. [16] HE, W. and CHEN, M., 2024. Advancing Urban Life: A Systematic Review of Emerging Technologies and Artificial Intelligence in Urban Design and Planning. Buildings, 14(3), pp. 835. [17] HONG, Z. and XIAO, K., 2024. Digital economy structuring for sustainable development: the role of blockchain and artificial intelligence in improving supply chain and reducing negative environmental impacts. Scientific Reports (Nature Publisher Group), 14(1), pp. 3912. [18] HU, H., JIANG, S., GOSWAMI, S.S. and ZHAO, Y., 2024. Fuzzy Integrated Delphi-ISM-MICMAC Hybrid Multi- Criteria Approach to Optimize the Artificial Intelligence (AI) Factors Influencing Cost Management in Civil Engineering. Information, 15(5), pp. 280. [19] IMRAN, A.L., YAN, H., ZHANG, C., WANG, G., HE, B., HAO, B., HAN, Y., WANG, B., BAO, R., TABINDA, N.S., JUNAID, N.C. and RAKIBUZZAMAN, M., 2024. A Review of Precision Irrigation Water-Saving Technology under Changing Climate for Enhancing Water Use Efficiency, Crop Yield, and Environmental Footprints. Agriculture, 14(7), pp. 1141. [20] IZQUIERDO-BUENO, I., MORAGA, J., CANTORAL, J.M., CARBÚ, M., GARRIDO, C. and GONZÁLEZ- RODRÍGUEZ, V.,E., 2024. Smart Viniculture: Applying Artificial Intelligence for Improved Winemaking and Risk Management. Applied Sciences, 14(22), pp. 10277. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 8s (2025) 525 https://internationalpubls.com [21] JABRAN, M., ALI, M.A., MUZAMMIL, S., ZAHOOR, A., ALI, F., HUSSAIN, S., MUHAE-UD-DIN, G., IJAZ, M. and GAO, L., 2024. Exploring the potential of nanomaterials (NMs) as diagnostic tools and disease resistance for crop pathogens. Chemical and Biological Technologies in Agriculture, 11(1), pp. 75. [22] JUAREZ-QUISPE, J., ROJAS-CHURA, E., ESPINOZA VIGIL, A.J., MILAGROS SOCORRO GUILLÉN MÁLAGA, YABAR-ARDILES, O., ANCO-VALDIVIA, J. and VALENCIA-FÉLIX, S., 2025. Advancing Sustainable Infrastructure Management: Insights from System Dynamics. Buildings, 15(2), pp. 210. [23] KAZEEM, K.O., OLAWUMI, T.O. and OSUNSANMI, T., 2023. Roles of Artificial Intelligence and Machine Learning in Enhancing Construction Processes and Sustainable Communities. Buildings, 13(8), pp. 2061. [24] KHALID, J., CHUANMIN, M., ALTAF, F., MUHAMMAD, M.S., SHAHID, K.K. and ASHRAF, M.U., 2024. AI- Driven Risk Management and Sustainable Decision-Making: Role of Perceived Environmental Responsibility. Sustainability, 16(16), pp. 6799. [25] LAUREN GENITH ISAZA DOMÍNGUEZ, FABIAN, V.C., ROBLES-GÓMEZ, A. and PASTOR-VARGAS, R., 2024. A Sustainable Educational Tool for Engineering Education Based on Learning Styles, AI, and Neural Networks Aligning with the UN 2030 Agenda for Sustainable Development. Sustainability, 16(20), pp. 8923. [26] LI, J., LIU, Z., HAN, G., DEMIAN, P. and OSMANI, M., 2024. The Relationship Between Artificial Intelligence (AI) and Building Information Modeling (BIM) Technologies for Sustainable Building in the Context of Smart Cities. Sustainability, 16(24), pp. 10848. [27] LI, Y., ANTWI-AFARI, M., ANWER, S., MEHMOOD, I., UMER, W., MOHANDES, S.R., IBRAHIM, Y.W., ABDUL-RAHMAN, M. and LI, H., 2024. Artificial Intelligence in Net-Zero Carbon Emissions for Sustainable Building Projects: A Systematic Literature and Science Mapping Review. Buildings, 14(9), pp. 2752. [28] LIFELO, Z., DING, J., NING, H., QURAT-UL-AIN and DHELIM, S., 2024. Artificial Intelligence-Enabled Metaverse for Sustainable Smart Cities: Technologies, Applications, Challenges, and Future Directions. Electronics, 13(24), pp. 4874. [29] LIU, Z., HE, Y., DEMIAN, P. and OSMANI, M., 2024. Immersive Technology and Building Information Modeling (BIM) for Sustainable Smart Cities. Buildings, 14(6), pp. 1765. [30] MD, N.R., KYU-HO, L., KARIM, M.R., HAQUE, M.A., BICAMUMAKUBA, E., DEY, P.K., YOUNG, Y.J. and SUN-OK, C., 2025. Trends of Soil and Solution Nutrient Sensing for Open Field and Hydroponic Cultivation in Facilitated Smart Agriculture. Sensors, 25(2), pp. 453.