SavedAdd your journal

Journals / Tekirdağ Ziraat Fakültesi Dergisi / 2026 / Cilt: 23 Sayı: 5

An Eco-Friendly Approach: The Modeling of Hot Water Applications with ANN and Sensitivity Analysis in Weed Control

Çevre Dostu Bir Yaklaşım: Yabancı Ot Kontrolünde Yapay Sinir Ağları (YSA) ve Hassasiyet Analizi ile Sıcak Su Uygulamalarının Modellenmesi

Elvan Koç(ARTVİN ÇORUH ÜNİVERSİTESİ, YUSUFELİ MESLEK YÜKSEKOKULU)0000-0002-9225-4336
Ramazan Gürbüz(IĞDIR ÜNİVERSİTESİ, IĞDIR ZİRAAT FAKÜLTESİ)0000-0003-3558-9823
Sefa Altıkat(IĞDIR ÜNİVERSİTESİ, IĞDIR ZİRAAT FAKÜLTESİ)0000-0002-3472-4424
Pages
1555–1569
Publication Date
2026-10-01
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results show that artificial neural networks can be used effectively, environmentally friendly, economically and innovatively as reliable prediction tools in thermal weed management to develop sustainable weed control strategies.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this research, it is aimed to accurately model hot water application, which is an environmentally friendly and innovative approach used in weed control in non-agricultural areas, with artificial neural networks.
📊
Key Findings & Data:As a result of the research, the weights of the plants above and below the ground after the hot water application were modeled with an accuracy of 98.6% and 96% respectively.
💡
Conclusion & Impact:The results show that artificial neural networks can be used effectively, environmentally friendly, economically and innovatively as reliable prediction tools in thermal weed management to develop sustainable weed control strategies.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Alternatif enerji · Sıcak su uygulaması · Yabancı ot yönetimi

Abstract

In this research, it is aimed to accurately model hot water application, which is an environmentally friendly and innovative approach used in weed control in non-agricultural areas, with artificial neural networks. For this purpose, application time, weed growth period and weed aboveground and belowground biomass weights were used as input parameters. In the study, the exotic species Amaranthus blitoides L., Chenopodium botrys L., and Heliotropium europaeum L. were used, and solar energy was utilized as an energy source for heating the water. Deep artificial neural networks were used in the models. As a result of the research, the weights of the plants above and below the ground after the hot water application were modeled with an accuracy of 98.6% and 96% respectively. The best models were obtained in ANN 15 architectures for the above-ground weight of the plant and ANN 7 architectures for below weight. In the sensitivity analysis, the effects of hot water application times and weeds growth stages on the success of the method were calculated as 28.5% - 30.8% and 28.4% - 31.6% respectively. In addition to these results, the effects of weed weights that above and below of the soil surface on the hot water application method were calculated as 39.9% and 40.8%, respectively. This study further explores the environmental implications and practical applications of using hot water for non-chemical weed control. The modelling process incorporated 15 different ANN architectures; ANN 15 and ANN 7 demonstrated the best performance. The experimental framework was based on a greenhouse pot trial involving three common broad-leaved weed species found in urban and non-agricultural areas. Sensitivity analyses revealed the interaction between biological growth stages and application timing, emphasising the adaptability of the method. The results show that artificial neural networks can be used effectively, environmentally friendly, economically and innovatively as reliable prediction tools in thermal weed management to develop sustainable weed control strategies.

Özet

Bu araştırmada, tarım dışı alanlarda yabancı ot kontrolünde kullanılan çevre dostu ve yenilikçi bir yaklaşım olan sıcak su uygulamasının yapay sinir ağları ile doğru biçimde modellenmesi amaçlanmıştır. Bu amaçla uygulama zamanı, yabancı ot büyüme dönemi ve yabancı otların toprak üstü ve toprak altı biyokütle ağırlıkları giriş parametreleri olarak kullanılmıştır. Araştırmada Amaranthus blitoides L., Chenopodium botrys L. ve Heliotropium europaeum L. yabancı ot türleri kullanılmış olup, suyun ısıtılmasında yenilenebilir bir enerji kaynağı olarak güneş enerjisinden yararlanılmıştır. Modellemelerde derin yapay sinir ağları kullanılmıştır. Araştırma sonucunda sıcak su uygulaması sonrası bitkilerin toprak üstü ve toprak altı ağırlıkları sırasıyla %98.6 ve %96 doğrulukla modellenmiştir. Bitkinin toprak üstü ağırlığı için ANN 15 mimarisinde, toprak altı ağırlığı için ise ANN 7 mimarisinde en iyi modeller elde edilmiştir. Duyarlılık analizinde sıcak su uygulama zamanlarının ve yabancı ot büyüme evrelerinin yöntemin başarısına etkileri sırasıyla %28.5 - %30.8 ve %28.4 - %31.6 olarak hesaplanmıştır. Bu sonuçlara ek olarak, sıcak su uygulama yöntemi üzerinde toprak yüzeyinin üstünde ve altında bulunan yabancı ot ağırlıklarının etkileri sırasıyla %39.9 ve %40.8 olarak hesaplanmıştır. Bu çalışma, kimyasal olmayan yabancı ot kontrolünde sıcak su kullanımının çevresel etkilerini ve pratik uygulamalarını daha ayrıntılı olarak araştırmaktadır. Modelleme süreci 15 farklı YSA mimarisini içermektedir; YSA 15 ve YSA 7 en iyi performansı göstermiştir. Deneysel çerçeve, kentsel ve tarım dışı alanlarda bulunan üç yaygın geniş yapraklı yabancı ot türünü içeren bir sera saksı denemesine dayanmaktadır. Duyarlılık analizleri, biyolojik büyüme aşamaları ile uygulama zamanlaması arasındaki etkileşimi ortaya koyarak yöntemin uyarlanabilirliğini vurgulamaktadır. Sonuçlar, yapay sinir ağlarının sürdürülebilir yabancı ot kontrol stratejilerini geliştirmek için termal yabancı ot yönetiminde güvenilir tahmin araçları olarak etkili, çevre dostu, ekonomik ve yenilikçi biçimde kullanılabileceğini göstermektedir.

🔖

Cite This Article

Koç, E., Gürbüz, R., Altıkat, S. (2026). An Eco-Friendly Approach: The Modeling of Hot Water Applications with ANN and Sensitivity Analysis in Weed Control. Tekirdağ Ziraat Fakültesi Dergisi, Cilt: 23 Sayı: 5, 1555–1569. https://doi.org/10.33462/jotaf.1684772

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (43)

  1. Aleboyeh, A., Kasiri, M. B., Olya, M. E. and Aleboyeh, H. (2008). Prediction of azo dye decolorization by UV/H2O2 using artificial neural networks. Dyes and Pigments, 77(2): 288-294.
  2. Anderson, R. L., Hansen, C. M., Thomas, C. and Hull, J. (1967). Flame for Weed Control–a Progress Report. Fourth Annual Symposium on Thermal Agriculture, National LP-Gas Association and Natural Gas Processars Association, Technical Papers, 27-28 January, P. 22-25, Kansas City, Missouri, U. S. A.
  3. Ascard, J. (1997). Flame weeding: effects of fuel pressure and tandem burners. Weed Research, 37(2): 77-86.
  4. Bakhshipour, A. and Jafari, A. (2018). Evaluation of support vector machine and artificial neural networks in weed detection using shape features. Computers and Electronics in Agriculture, 145: 153-160.
  5. Bauer, M. V., Marx, C., Bauer, F. V., Flury, D. M., Ripken, T. and Streit, B. (2020). Thermal weed control technologies for conservation agriculture A review. Weed Research, 60(4): 241-250.
  6. Cengiz, M. F., Basancelebi, O. and Kitis, Y. E. (2017). Glyphosate residues in drinking waters and adverse health effects. The Türkiye Journal of Occupational/Environmental Medicine and Safety, 2(1(3)): 247-258.
  7. Cisneros, J. J. and Zandstra, B. H. (2008). Flame weeding effects on several weed species. Weed Technology, 22(2): 290-295.
  8. Collins, M. (1999). Thermal Weed Control, a Technology with a Future. 12th Twelfth Australian Weeds Conference Proceedings Weed Management into the 21st Century: Do We Know Where We're Going, 12-16 September, P. 25-28, Hobart, Tasmania, Australia.
  9. Cox, C. (2004). Herbicide factsheet: glyphosate. Journal of Pesticide Reform, 24: 10–15.
  10. Çelebi, Ş. Z., Arvas, Ö., Çelebi, R. and Yılmaz, İ. H. (2010). Determination of the performance of English ryegrass (Lolium perenne L.) in the green area established with wastewater treatment sludge. Tekirdağ Journal of Agricultural Faculty, 7(3): 111-118. (In Turkish)
  11. Daniell, J. W., Chappell, W. E. and Couch, H. B. (1969). Effect of sublethal and lethal temperature on plant cells. Plant Physiology, 44(12): 1684-1689.
  12. De Cauwer, B., Bogaert, S., Claerhout, S., Bulcke, R. and Reheul, D. (2015). Efficacy and reduced fuel use for hot water weed control on pavements. Weed Research, 55(2): 195-205.
  13. De Cauwer, B., De Keyser, A., Biesemans, N., Claerhout, S. and Reheul, D. (2016). Impact of wetting agents, time of day and periodic energy dosing strategy on the efficacy of hot water for weed control. Weed Research, 56(4): 323-334.
  14. Dyrmann, M., Karstoft, H. and Midtiby, H. S. (2016). Plant species classification using deep convolutional neural network. Biosystems Engineering, 151: 72-80.
  15. Gürbüz, R., Koç, E. and Güney, A. (2019). Thermal Weed Control in Non-Agricultural Areas. 6th International Congress of Vocational and Technical Sciences.11-12 April, P.127-128, Iğdır University, Iğdır, Türkiye. (In Turkish)
  16. Hansson D. (2002). Hot Water for Weed Control on Urban Hard Surfac Areas. 5th EWRS Workshop on Physical and Cultural Weed Control, 1 January, P. 242–243, Pisa, Italy.
  17. Hansson, D. and Ascard, J. (2002). Influence of developmental stage and time of assessment on hot water weed control. Weed Research, 42(4): 307-316.
  18. Hansson, D. and Mattsson, J. E. (2002). Effect of drop size, water flow, wetting agent and water temperature on hot-water weed control. Crop Protection, 21(9): 773-781.
  19. Huang, H., Deng, J., Lan, Y., Yang, A., Deng, X. and Zhang, L. (2018). A fully convolutional network for weed mapping of unmanned aerial vehicle (UAV) imagery. PloS one, 13(4): e0196302.
  20. Huebnerova, Z. and Michalek, J. (2014). Analysis of daily average PM10 predictions by generalized linear models in Brno, Czech Republic. Atmospheric Pollution Research, 5(3): 471-476.
  21. Jeon, H. Y., Tian, L. F. and Zhu, H. (2011). Robust crop and weed segmentation under uncontrolled outdoor illumination. Sensors, 11(6): 6270-6283.
  22. Jodoin, Y., Lavoie, C., Villeneuve, P., Theriault, M., Beaulieu, J. and Belzile, F. (2008). Highways as corridors and habitats for the invasive common reed Phragmites australis in Quebec, Canada. Journal of Applied Ecology, 45(2): 459-466.
  23. Kempenaar, C., Lotz, L. A. P., Van der Horst, C. L. M., Beltman, W. H. J., Leemans, K. J. M. and Bannink, A. D. (2007). Trade off between costs and environmental effects of weed control on pavements. Crop Protection, 26(3): 430-435.
  24. Kitiş, Y. E. and Gürbüz, R. (2021). Weed Control Using Thermal Methods. In: Current Topics in Weed Science, Eds: Mennan, H. and Pala, F., İksad Publications, Türkiye. (In Turkish)
  25. Koç, E. (2024). Bibliometric Analysis of Studies on Hot Water in Non-Agricultural Areas. 6th International Azerbaijan Congress on Life, Engineering, Mathematical, and Applied Sciences, 20–22 March, P. 349, Azerbaijan. (In Turkish)
  26. Koç, E. (2025a). Publication trends in thermal weed control: A bibliometric analysis. ISPEC Journal of Science Institute, 4(2): 150-167. (In Turkish)
  27. Koç, E. (2025b). Studies on the possibility of using hot water in weed control in non-agricultural areas. (PhD Thesis). Iğdır University, Institute of Science, Iğdır,Türkiye.
  28. Koç, E. (2025c). Analysis of Scientific Publications on Weed Research. Turkish Journal of Biodiversity, 8(2): 114-130. (In Turkish)
  29. Koç, E. and Gürbüz, R. (2017). Impact of Herbicides on Environment Human and Animal Health. I. International Agricultural Science Congress, 9-12 May, P. 560, Van, Türkiye.
  30. Levitt, J. (1980). Responses of Plants to Environmental Stress, Volume 1: Chilling, Freezing and High Temperature Stresses. Academic Press, New York, U. S. A.
  31. Li, P., Peng, C., Wang, M., Li, W., Zhao, P., Wang, K. and Zhu, Q. (2017). Quantification of the response of global terrestrial net primary production to multifactor global change. Ecological Indicators, 76: 245-255.
  32. Olsen, A., Konovalov, D. A., Philippa, B., Ridd, P., Wood, J. C., Johns, J. and White, R. D. (2019). DeepWeeds: A multiclass weed species image dataset for deep learning. Scientific Reports, 9(1): 2058.
  33. Özkil, M. and Üremiş, İ. (2023). Determination of emergence depth and germination rates of Ipomoea triloba L. and Convolvulus arvensis L. seeds buried at different depths in soil. Tekirdağ Journal of Agricultural Faculty, 20(4): 811-820. (In Turkish)
  34. Porterfield, J. G., Batchelder, D. G., Bashford, L. E. O. N. A. R. D. and McLaughlin, G. (1971). Two Stage Thermal Defoliation. National LP-Gas Association and Natural Gas Processors Association, Dallas, TX, P.32-34, U. S. A.
  35. Rask, A. M. and Kristoffersen, P. (2007). A review of non‐chemical weed control on hard surfaces. Weed Research, 47(5): 370-380.
  36. Rask, A.M. (2012). Non-chemical weed control on hard surfaces: An investigation of long-term effects of thermal weed control methods. Forest and Landscape Research, 52: 1–156.
  37. Rivas-Garcia, T., Espinosa-Calderón, A., Hernández-Vázquez, B. and Schwentesius-Rindermann, R. (2022). Overview of environmental and health effects related to glyphosate usage. Sustainability, 14(11): 6868.
  38. Silva, T. S., de Freitas Souza, M., da Silva Teófilo, T. M., Dos Santos, M. S., Porto, M. A. F., Souza, C. M. M. and Silva, D. V. (2019). Use of neural networks to estimate the sorption and desorption coefficients of herbicides: A case study of diuron, hexazinone, and sulfometuron-methyl in Brazil. Chemosphere, 236: 124333.
  39. Stepanovic, S. V. (2013). Positioning an innovative flame-weeding technology into crop production. (MSc. Thesis). University of Nebraska–Lincoln, Department of Agronomy and Horticulture, Lincoln, Nebraska, U. S. A.
  40. Tepe, I. (1998). Problematic Weeds in Agricultural and Non-Agricultural Areas in Türkiye and Their Control. Yüzüncü Yıl University Press. Van, Türkiye. (In Turkish)
  41. Vaidhehi, M. and Malathy, C. (2022). Retracted Article: An unique model for weed and paddy detection using regional convolutional neural networks. Acta Agriculturae Scandinavica, Section B-Soil and Plant Science, 72(1): 463-475.
  42. Yu, J., Sharpe, S. M., Schumann, A. W. and Boyd, N. S. (2019). Detection of broadleaf weeds growing in turfgrass with convolutional neural networks. Pest Management Science, 75(8): 2211-2218.
  43. Zadoks, J. C., Chang, T. T. and Konzak, C. F. (1974). A decimal code for the growth stages of cereals. Weed research, 14(6): 415-421.