Forecasting urban forest recreation areas in Turkey using machine learning methods

Abstract

Recreation is the process of revitalizing and renewing human existence through optional activities, serving as a broad description. It has prominently arisen as a reaction to personal requirements for stress reduction, especially in developed urban areas. Engaging in this recreational activity provides a way to utilize one's spare time, providing refreshment for both the physical and mental aspects, whether done alone or with others, in countryside or city environments. Urban forests are important leisure places within city environments. An expanded presence of urban forest places can greatly enhance the general well-being of society. The estimation of urban forest areas in the future may receive increased attention, leading to measures to extend current areas or prepare for future activities and services. We utilized official statistics from the years 2013 to 2021, sourced from the Republic of Turkey official website. Ministry of Agriculture and Forestry's General Directorate of Forestry. We used statistics that contained information about urban forests, classified as Type D recreational areas, to create a dataset. We performed provincial-level area projections for the year 2021. Using the KNIME platform, we used three different analysis techniques: linear regression analysis, gradient-boosted regression trees and artificial neural networks. It is seen that the results of linear regression and artificial neural networks are close to each other and give good results. The peak performance was attained using artificial neural networks, resulting in an R2 score of 0.99. This study differs from other similar projects by concentrating on calculating urban forest recreational spaces per province throughout Turkey, using data provided by government agencies. The accomplishments highlight the ability to make reliable predictions about future forest resources by using analogous forecasts in the upcoming years.

Keywords

• Recreation areas
• Urban forests
• Linear regression analysis
• Gradient boosted regression trees
• Artificial neural network

References

1. [1] P. L. Winter, S. Selin, L. Cerveny and K. Bricker, “Outdoor recreation, nature-based tourism, and sustainability,” Sustainability, vol. 12, no. 1, pp. 81, 2019, doi: 10.3390/su12010081.
2. [2] Ç. Kılıçaslan, ‟Ortaca kenti rekreasyon alanlarının mevcut durumu ve Muğla Üniversitesi Ortaca Meslek Yüksekokulu öğrencilerinin rekreasyon alanlarına yönelik beklentileri,” Düzce Üniversitesi Ormancılık Dergisi, vol 4, no. 1-2, pp. 3-16, 2008.
3. [3] S. Uzun and H. Müderrisoğlu, “Kirsal ve kentsel alanlardaki parklarda kullanici memnuniyeti; Gölcük orman içi dinlenme alani ve İnönü Parkı örneği,” Düzce Üniversitesi Orman Fakültesi Ormancılık Dergisi, vol. 3, no. 2, pp. 84-101, 2007.
4. [4] H. Akyüz, M. Kul and F. Yaşartürk, “Rekreasyon açısından ormanlar ve çevre,” International Journal of Sport Culture and Science, vol 2, no. (Special Issue 1), pp. 881-890, 2016.
5. [5] M. G. Rupert, S. H. Cannon and J. E. Gartner, “Using logistic regression to predict the probability of debris flows occurring in areas recently burned by wild land fires,” US Geological Survey Open-File Report, vol. 500, no. 1, 2003.
6. [6] T. Bjerke, C. T. and J. Kleiven, “Outdoor recreation interests and environmental attitudes in Norway,” Managing leisure, vol. 11, no. 2, pp. 116-128, 2006, doi: 10.1080/13606710500520197.
7. [7] Y. Nong and Q. Du, “Urban growth pattern modeling using logistic regression,” Geo-spatial Information Science, vol. 14, no. 1, pp. 62-67, 2011, doi: 10.1007/s11806-011-0427-x.
8. [8] H. M. Shaikh, M. S. Patterson, B. Lanning, M. R. Umstattd Meyer and C. A. Patterson, “Assessing college students’ use of campus recreation facilities through individual and environmental factors,” Recreational Sports Journal, vol. 42, no. 2, pp. 145-159, 2018, doi: 10.1123/rsj.2017-0.

9. [9] K. Kozlov, A. Singh, J. Berger et al. “Non-linear regression models for time to flowering in wild chickpea combine genetic and climatic factors,” BMC Plant Biol, vol. 19, no. 94, pp. 1-14, 2019.
10. [10] N. Başaran, D. K. Matcı and U. Avdan, “Using multiple linear regression to analyze changes in forest area: the case study of Akdeniz Region,” International Journal of Engineering and Geosciences, vol. 7, no. 3, pp. 247-263, 2022, doi: 10.26833/ijeg.976418.
11. [11] Z. Liu, C. Peng, T. Work, J. N. Candau, A. DesRochers and D. Kneeshaw, “Application of machine-learning methods in forest ecology: recent progress and future challenges,” Environmental Reviews, vol. 26, no 4, pp. 339-350, 2018, doi: 10.1139/er-2018-0034.
12. [12] Q. Zhao, S. Yu, F. Zhao, L. Tian and Z. Zhao, “Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments,” Forest Ecology and Management, vol. 434, pp. 224-234, 2019, doi: 10.1016/j.foreco.2018.12.019.
13. [13] J.V. Solórzano and Y. Gao, “Forest disturbance detection with seasonal and trend model components and machine learning algorithms,” Remote Sensing, vol. 14, no. 3, pp. 803, 2022, doi: 10.3390/rs14030803.
14. [14] S. G. Gocheva-Ilieva, A. V. Ivanov and I. E. Livieris, “High performance machine learning models of large scale air pollution data in urban area,” Cybernetics and Information Technologies, vol. 20, no. 6, pp. 49-60, 2020, doi: 10.2478/cait-2020-0060.
15. [15] M. Pourshamsi, M. Garcia, M. Lavalle and H. Balzter, “A machine-learning approach to PolInSAR and LiDAR data fusion for improved tropical forest canopy height estimation using NASA AfriSAR Campaign data,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 11, no. 10, pp. 3453-3463, 2018, doi: 10.1109/JSTARS.2018.2868119.
16. [16] X. Liu, S. Liang, B. Li, H. Ma and T. He, “Mapping 30 m fractional forest cover over China’s Three-North Region from Landsat-8 data using ensemble machine learning methods,” Remote Sensing, vol. 13, no. 13, pp. 2592, 2021, doi: 10.3390/rs13132592.
17. [17] K. Manley, and B. N. Egoh,” Mapping and modeling the impact of climate change on recreational ecosystem services using machine learning and big data”, Environmental Research Letters, vol. 17, no. 5, pp 054025, 2022.
18. [18] C. Chen, Z. Shen, Y. Weng, S. You, J. Lin, S. Li, and K. Wang, “Modeling Landslide Susceptibility in Forest-Covered Areas in Lin’an, China, Using Logistical Regression, a Decision Tree, and Random Forests”, Remote Sensing, vol. 15 no. 18, pp 4378, 2023.
19. [19] A. Adhikari, C. R. Montes, and A. Peduzzi, “A comparison of modeling methods for predicting forest attributes using LiDAR metrics”, Remote Sensing, vol. 15, no. 5, pp 1284, 2023.
20. [20] Y. Zhou, J. Hu, M. Liu, and G. Xie, “Predicting Sub-Forest Type Transition Characteristics Using Canopy Density: An Analysis of the Ganjiang River Basin Case Study”, Forests, vol. 15, no. 2, pp 274, 2024.
21. [21] M. Kaya and S. A. Özel, “Açık kaynak kodlu veri madenciliği yazılımlarının karşılaştırılması,” Akademik Bilişim, pp. 1-8, 2014.
22. [22] Republic of Turkey Ministry of Agriculture and Forestry General Directorate of Forestry, “Official statistics.” ogm.com, https://www.ogm.gov.tr/tr/e-kutuphane/resmi-istatistikler (accesed Feb. 1, 2023).
23. [23] A.O. Sykes, “An introduction to regression analysis,” Coase-Sandow Working Paper Series in Law and Economics, 1993.
24. [24] S. Kılıç, “Doğrusal regresyon analizi,” Journal of Mood Disorders, vol. 3, no. 2, pp. 90-92, 2013, doi: 10.5455/jmood.20130624120840.
25. [25] S. Dörterler, “Developing a prediction model with the Battle Royale Optimization Algorithm,” in International Research in Engineering Sciences III, vol. 1, M. Kamanlı, Eds. Konya, Turkey: Egitim Publishing, 2022, pp. 5-19.
26. [26] D. Maulud and A. M. Abdulazeez, “A review on linear regression comprehensive in machine learning,” Journal of Applied Science and Technology Trends, vol. 1, no. 4, pp. 140-147, 2020, doi: 10.38094/jastt1457.
27. [27] Ö. G. Uzut and S. Buyrukoğlu, "Veri̇ madenci̇li̇ği̇ algori̇tmalari ile gayri̇menkul fi̇yatlarinin tahmi̇ni̇,” Euroasia Journal of Mathematics, Engineering, Natural & Medical Sciences, vol. 7, no. 9, pp. 77-84, doi: 10.38065/euroasiaorg.81.
28. [28] H. Alshari, A. Saleh and A. Odabas, “CPU performansı için gradyan artırımlı karar ağacı algoritmalarının karşılaştırılması,” Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, vol. 37, no. 1, pp. 157-168, 2021.
29. [29] Y. Shin, “Application of boosting regression trees to preliminary cost estimation in building construction projects,” Computational intelligence and neuroscience, vol. 2015, pp. 1-1, 2015, doi: 10.1155/2015/149702.
30. [30] İ. Pençe, A. Kalkan and M. Ş. Çeşmeli, “Turkey sanayi elektrik enerjisi tüketiminin 2017-2023 dönemi için yapay sinir ağları ile tahmini,” Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi, vol. 3, no. 2, pp. 206-228, 2019, doi: 10.31200/makuubd.538878.
31. [31] R. M. Sadek, S. A. Mohammed, A. R. K. Abunbehan, A. K. H. A. Ghattas, M. R. Badawi, M. N. Mortaja and S. S. Abu-Naser, “Parkinson's disease prediction using artificial neural network,” International Journal of Academic Health and Medical Research, vol. 3, no. 1, pp. 1-8, 2019.
32. [32] K. Öztürk and M. E. Şahin, “Yapay sinir ağları ve yapay zekâ’ya genel bir bakış,” Takvim-i Vekayi, vol. 6, no. 2, pp. 25-36, 2018.
33. [33] K. Y. Lee, K. H. Kim, J. J. Kang, S. J. Choi, Y. S. Im, Y. D. Lee, and Y. S. Lim, “Comparison and analysis of linear regression & artificial neural network”, International Journal of Applied Engineering Research, vol. 12, no. 20, pp. 9820-9825, 2017.
34. [34] D. Özdemir, S. Dörterler and D. Aydın, “A new modified artificial bee colony algorithm for energy demand forecasting problem,” Neural Computing and Applications, vol. 34, no. 20, pp.17455-17471, 2022.
35. [35] D. Özdemir and S. Dörterler, “An adaptive search equation-based artificial bee colony algorithm for transportation energy demand forecasting,” Turkish Journal of Electrical Engineering and Computer Sciences, vol. 30, no. 4, pp. 1251-1268, 2022.