Çevresel İzleme ve Yönetim için Yapay Zekâ ve Makine Öğrenmesi: Açık Veri Setleri Kullanılarak Karşılaştırmalı Kıyaslama Analizi

Abstract

Bu çalışma, çevresel izleme ve yönetim alanında Yapay Zekâ (YZ) ve Makine Öğrenmesi (MÖ) tekniklerine yönelik yapılandırılmış bir kıyaslama ve karşılaştırmalı analiz sunmaktadır. Kamuya açık veri kümeleri ve yeniden üretilebilir modelleme iş akışları kullanılarak, hava kalitesi, su kirliliği, ormansızlaşma ve biyolojik çeşitlilik izleme dâhil olmak üzere birden fazla çevresel alanda temsili YZ modelleri eğitilmiş veya yeniden uygulanmış ve değerlendirilmiştir. Kullanılan veri kümeleri arasında Air Quality Open Dataset, AquaSat, Global Forest Watch ve iNaturalist yer almakta olup, temel çevresel alanları ele almak amacıyla birden fazla YZ modeli geliştirilmiş, eğitilmiş ve doğrulanmıştır. Hava kalitesi tahmini için Rastgele Orman (Random Forest), su kirliliği tespiti için Evrişimli Sinir Ağları (CNN), ormansızlaşma izleme için Uzun Kısa Süreli Bellek (LSTM) ağları ve yaban hayatı tür tanımlaması için Destek Vektör Makineleri (SVM) kullanılmıştır. Model performansı; doğruluk (accuracy), kesinlik (precision), duyarlılık (recall), Ortalama Mutlak Hata (MAE), Kök Ortalama Kare Hatası (RMSE) ve belirleme katsayısı (R²) metrikleri kullanılarak değerlendirilmiştir. Elde edilen sonuçlar, YZ tabanlı yöntemlerin geleneksel izleme yaklaşımlarına kıyasla anlamlı derecede üstün performans gösterdiğini ortaya koymuş; su kirliliği tespitinde %95,1’e, hava kalitesi tahmininde ise %92,4’e varan doğruluk oranlarına ulaşılmış ve alanlar genelinde doğruluk artışlarının %17,7 ile %23 arasında değiştiği belirlenmiştir. PM2.5 tahmininde Gradyan Artırma (Gradient Boosting) yöntemi %93,2 doğruluk (R² = 0,92) elde ederken, YOLOv5 modeli yasa dışı ağaç kesimi tespitinde %94 algılama oranına ulaşmıştır. Çevresel etki değerlendirmeleri, YZ entegrasyonu sonrasında önemli iyileşmeler olduğunu göstermiş; yasa dışı ağaç kesiminde %41,7 azalma ve su kirliliği olaylarında %44,2 düşüş kaydedilmiştir. Dağıtım analizleri, üç yıllık süreçte %175’e varan Yatırım Getirisi (ROI) ve izleme görevleri genelinde %68 ile %73 arasında değişen zaman tasarrufları ile yüksek maliyet etkinliğine işaret etmiştir. Bu bulgular, YZ ve MÖ’nün yalnızca öngörü doğruluğunu artırmakla kalmayıp aynı zamanda somut çevresel ve ekonomik faydalar sağladığını ortaya koymakta ve sürdürülebilir çevresel yönetişim için temel araçlar olarak taşıdıkları potansiyeli vurgulamaktadır.

Keywords

• Artificial Intelligence
• Environmental Monitoring
• Machine Learning
• Sustainability
• Technology Adoption.

Artificial Intelligence and Machine Learning for Environmental Monitoring and Management: A Comparative Benchmarking Analysis Using Public Datasets

Abstract

This study presents a structured benchmarking and comparative analysis of Artificial Intelligence (AI) and Machine Learning (ML) techniques for environmental monitoring and management. Using publicly available datasets and reproducible modeling workflows, representative AI models were trained or re-implemented and evaluated across multiple environmental domains, including air quality, water pollution, deforestation, and biodiversity monitoring. The available used datasets include the Air Quality Open Dataset, AquaSat, Global Forest Watch, and iNaturalist, multiple AI models and were developed, trained, and validated to address key environmental domains. Random Forest was applied for air quality prediction, Convolutional Neural Networks (CNNs) for water pollution detection, Long Short-Term Memory (LSTM) networks for deforestation monitoring, and Support Vector Machines (SVMs) for wildlife species identification. Model performance was evaluated using accuracy, precision, recall, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R²) metrics. Results showed that AI-based methods significantly outperformed traditional monitoring approaches, achieving up to 95.1% accuracy in water pollution detection and 92.4% accuracy in air quality prediction, with accuracy improvements ranging from 17.7% to 23% across domains. Gradient Boosting achieved a 93.2% accuracy in PM2.5 prediction (R² = 0.92), while YOLOv5 reached a 94% detection rate for illegal logging. Environmental impact assessments revealed substantial reductions after AI integration, including a 41.7% decrease in illegal logging and a 44.2% decline in water contamination incidents. Deployment analysis indicated high-cost efficiency, with Return on Investment (ROI) values up to 175% over three years and time savings between 68% and 73% across monitoring tasks. These findings confirm that AI and ML not only enhance predictive precision but also deliver tangible environmental and economic benefits, underscoring their potential as essential tools for sustainable environmental governance.

Keywords

• Artificial Intelligence
• Environmental Monitoring
• Machine Learning
• Sustainability
• Technology Adoption.

References

1. Akeem, A., & Akintola, A. (2024). AI-driven monitoring systems for bioremediation: Real-time data analysis and predictive modelling. World Journal of Advanced Research and Reviews, 24(1), 3099. https://doi.org/10.30574/wjarr.2024.24.1.3099
2. Alotaibi, E., & Nassif, N. (2024). Artificial intelligence in environmental monitoring: In-depth analysis. Discover Artificial Intelligence, 1(1), 198–201. https://doi.org/10.1007/s44163-024-00198-1
3. Alqahtani, O., & Kshirsagar, P. R. (2024). An IoT-based framework for prediction of environment quality using artificial intelligence. Journal of Advanced Technological Systems, 5(2), 102–110. https://doi.org/10.1109/atsip62566.2024.10639027
4. Martyszunis, A., Loga, M., & Przeździecki, K. (2024). Using machine learning for the assessment of ecological status of unmonitored waters in Poland. Dental Science Reports, 12(3), 215–220. https://doi.org/10.1038/s41598-024-74511-4
5. Patoucha, A., & Γαρείου, Ζ. (2024). The role of artificial intelligence in environmental sustainability. E3S Web of Conferences, 58(1), 1011. https://doi.org/10.1051/e3sconf/202458511011
6. Asif, R., Paul, A., Rahman, M. S., Bin Al Islam, S. M. A., Parson, P., & Karmakar, S. (2024). Artificial Intelligence (AI) for environmental sustainability: A concise review of technology innovations in energy, transportation, biodiversity, and water management. Journal of Technology Innovations in Energy, 3(2), 953–960. https://doi.org/10.56556/jtie.v3i2.953
7. Anifowose, B., & Anifowose, F. (2024). Artificial intelligence and machine learning in environmental impact prediction for soil pollution management – Case for EIA process. Environmental Advances, 15(3), 100554. https://doi.org/10.1016/j.envadv.2024.100554
8. Chuchu, S. K., Chinnem, R. M., Kumar, B. S., Lavanya, N. S. P., & Banerjee, D. (2024). Novel deep learning approaches to environmental management with sustainability. International Journal of Computer Science, 62(3), 932–939. https://doi.org/10.1109/ic3se62002.2024.10593298

9. Manongga, D., Rahardja, U., Sembiring, I., Aini, Q., & Wahab, A. (2024). Improving the air quality monitoring framework using artificial intelligence for environmentally conscious development. HighTech and Innovation Journal, 5(3), 17–21. https://doi.org/10.28991/hij-2024-05-03-017
10. Majeed, D. A., Ahmad, H. B., Hani, A. A., Zeebaree, S. R. M., Abdulrahman, S. M., Asaad, R. R., & Sallow, A. B. (2024). Data analysis and machine learning applications in environmental management. Journal of Environmental Information Technology, 8(2), 32769–32775. https://doi.org/10.22437/jiituj.v8i2.32769
11. Dwivedi, N. D., Mahanty, G., & Dwivedi, V. K. (2024). Intelligent conservation. Advances in Systems Analysis, Software Engineering, and High-Performance Computing, 9(1), 80–90. https://doi.org/10.4018/979-8-3693-1702-0.ch011
12. Di Ciaccio, F. (2024). The supporting role of artificial intelligence and machine/deep learning in monitoring the marine environment: A bibliometric analysis. Ecological Questions, 35(1), 5–11. https://doi.org/10.12775/eq.2024.005
13. Hazimze, H., Gaou, S., & Akhlil, K. (2024). Smart environmental monitoring and COVID-19. Advances in Environmental Engineering and Green Technologies, 14(2), 155–160. https://doi.org/10.4018/979-8-3693-3807-0.ch014
14. Singh, M., Arora, V., & Kulshreshta, K. (2024). AI and the environment. Practice, Progress, and Proficiency in Sustainability, 1(1), 1–9. https://doi.org/10.4018/979-8-3693-6336-2.ch001
15. González, M. G., Paniagua Arís, E., & Martı́nez-Béjar, R. (2024). AI-based environmental information system for decision-making in public administrations. Environmental Science Advances, 2(2), 12–20. https://doi.org/10.1201/9781003501152-7
16. Khan, M. R. (2024). Advances in architectures for deep learning: A thorough examination of present trends. Deleted Journal, 1(1), 30–36. https://doi.org/10.60087/jaigs.v1i1.p30
17. Arowolo, M. E., Aaron, W. C., Kugbiyi, O., Ubi, S. E., Iloh, D., Aguma, C. P., & Olagunju, A. O. (2024). Integrating AI enhanced remote sensing technologies with IoT networks for precision environmental monitoring and predictive ecosystem management. World Journal of Advanced Research and Reviews, 23(2), 2573–2585. https://doi.org/10.30574/wjarr.2024.23.2.2573
18. Onyebuchi, N. C., Biu, P. W., Umoh, A. A., Obaedo, B. O., Adegbite, A. O., & Abatan, A. (2024). Reviewing the role of AI in environmental monitoring and conservation: A data-driven revolution for our planet. World Journal of Advanced Research and Reviews, 21(1), 2720–2731. https://doi.org/10.30574/wjarr.2024.21.1.2720
19. Arabelli, R., Boddepalli, E., Buradkar, M., Goriparti, N. V. S., & Chakravarthi, M. K. (2024). IoT-enabled environmental monitoring system using AI. Advances in Computational AI, 6(3), 213–220. https://doi.org/10.1109/accai61061.2024.10602131
20. Shanmugapriya, N. (2024). Synergizing remote sensing, geospatial intelligence, applied nonlinear analysis, and AI for sustainable environmental monitoring. Communications on Applied Nonlinear Analysis, 31(3), 1222–1226. https://doi.org/10.52783/cana.v31.1222
21. Pratap, S., & Venkatesh, K. (2024). The role of AI in enhancing green management and advancing digital lean practices for sustainable efficiency. ShodhKosh Journal of Visual and Performing Arts, 5(6), 1725–1730. https://doi.org/10.29121/shodhkosh.v5.i6.2024.1725
22. Popescu, M. S., Sheikh, M., Wani, O. A., Kumar, S. S., Sharma, A., Arya, V. M., Kirkham, B., Hou, D., & Bolan, N. (2024). Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management. Frontiers in Environmental Science, 13(2), 1336088–1340000. https://doi.org/10.3389/fenvs.2024.1336088
23. Tatiraju, T., Dhineshkumar, K., Mishra, H., & Sekar, C. P. (2024). Machine learning-enhanced wireless sensor networks for real-time environmental monitoring. International Journal of BIM & Engineering Science, 10(1), 103–110. https://doi.org/10.54216/ijbes.100103
24. Vijayalakshmi, A., Ebenezer, E. A. B., Rubi, J., Dhivya, K., & Ram, A. S. (2024). Machine learning-based prediction and analysis of air and noise pollution in urban environments. International Journal of Environmental Sciences, 60(1), 25644–25650. https://doi.org/10.1109/icscss60660.2024.10625644
25. Jain, V., & Mitra, A. (2024). Integrative innovations. Practice, Progress, and Proficiency in Sustainability, 1(1), 45–49. https://doi.org/10.4018/979-8-3693-6336-2.ch014
26. Suganya, A., Suryawanshi, M. A., Bagal, M. V., Rawat, R., Kaliappan, S., & Manikandan, G. (2024). Innovative system for environmental monitoring with connected sensors and data analysis for chemical pollutants. 2024 IEEE Conference Proceedings, 1–6. https://doi.org/10.1109/icisaa62385.2024.10828896
27. Majeed, D., Ahmad, H. B., Hani, A. A., Zeebaree, S. R. M., Abdulrahman, S. M., Asaad, R. R., & Sallow, A. B. (2024). Data analysis and machine learning applications in environmental management. Journal of Environmental Information Technology, 8(2), 32769–32775. https://doi.org/10.22437/jiituj.v8i2.32769
28. Hegde, N. R., & Bargavi, S. M. (2024). Smart conservation: Integrating AI for enhanced wildlife monitoring. International Research Journal of Computer Science. https://doi.org/10.26562/irjcs.2024.v1101.10
29. Ojji, S. O. (2024). Emerging technology integration – Artificial intelligence (AI) and machine learning (ML) for predictive analysis for safety and toxicity assessment in environmental toxicology. International Journal of Scientific Research and Management. https://doi.org/10.18535/ijsrm/v12i05.ec03
30. Rahman, M. A., Emon, M. M. H., Khan, T., Hamid, A. B. A., & Yaakub, N. I. (2024). Eco-intelligence. In Advances in Environmental Engineering and Green Technologies (pp. 31–62). https://doi.org/10.4018/979-8-3693-9879-1.ch002
31. Shuford, J. (2024). Interdisciplinary perspectives: Fusing artificial intelligence with environmental science for sustainable solutions. Deleted Journal, 1(1), 106–123. https://doi.org/10.60087/jaigs.v1i1.87
32. Tatiraju, T., Dhineshkumar, K., Mishra, H., & Sekar, C. P. (2024). Machine learning-enhanced wireless sensor networks for real-time environmental monitoring. International Journal of BIM & Engineering Science, 10(1), 18–25. https://doi.org/10.54216/ijbes.100103
33. Olodu, D. D., & Okpoko, J. S. (2023). Mechanical properties of alloys and thermoplastic composites derived from non-biodegradable municipal solid waste. Uniport Journal of Engineering and Scientific Research (UJESR), 8(1), 61–74. ISSN: 2616-1192
34. Akter, M. (2024). Interdisciplinary outlook: Integrating artificial intelligence with environmental science for sustainable solutions. Deleted Journal, 1(1), 18–23. https://doi.org/10.60087/jaigs.v1i1.p23
35. Olodu, D. D., Ihenyen, O. I., & Inegbedion, F. (2025). Advances in renewable energy systems: Integrating solar, wind, and hydropower for a carbon-neutral future. International Journal of Novel Frontiers in Engineering, Science and Technology (IJONFEST), 3(1), 14–24. https://doi.org/10.61150/ijonfest.2025030102
36. Khosravi, A., & Ashkpour, M. (2024). Machine learning and digital innovation for managing and monitoring water resources. In Advances in Environmental Engineering and Green Technologies Book Series (pp. 241–284). https://doi.org/10.4018/979-8-3693-9879-1.ch010
37. Olodu, D. D., Ihenyen, O. I., & Erameh, A. (2025). Comprehensive analysis of green hydrogen production: Technologies, costs, environmental impacts, and policy frameworks. Journal of Sustainable and Advanced Technologies (JSAT), 3(1), 1–12. https://doi.org/10.63063/jsat.1611951
38. Olodu, D. D., Inegbedion, F., & Ihenyen, O. I. (2025). Smart water management systems: Engineering innovations for water conservation and distribution. Journal of Sustainable and Advanced Technologies (JSAT), 3(1), 13–31. https://doi.org/10.63063/jsat.1613583
39. Olodu, D. D., Erameh, A., & Ihenyen, O. I. (2025). A multidimensional assessment of waste-to-energy technologies: Economic feasibility, social acceptance, and future trends of gasification and pyrolysis. International Journal of Modern Science and Innovative Technology (IJMSIT), 9(1), 14–22. https://doi.org/10.36287/ijmsit.9.1.3
40. Olodu D. D. & Erameh, A. (2023). Waste to Energy: Review on the Development of Land Fill Gas for Power Generation in Sub-Saharan Africa, Black Sea Journal of Engineering and Science, 6(3). 296–307. https://doi.org/10.34248/bsengineering.1195247.