Estimation of Turbidity in the Cheney Reservoir Using Landsat 8 Images: A Comparison of Regression, MARS, and TreeNet Methods

Year 2024, , 172 - 185, 26.09.2024

Ömer Dilmen , Sinan Nacar , Esra Tunç Görmüş , Adem Bayram

https://doi.org/10.48123/rsgis.1451338

Abstract

Monitoring water quality in reservoirs is crucial for determining the suitability of water for its intended use and protecting aquatic life. One of the most commonly used indicators of reservoir water quality is turbidity. As a cost-effective and quick alternative to traditional monitoring methods, studies with remote sensing have gained traction. This study aims to develop a model to estimate turbidity in the Cheney Reservoir (Kansas, USA) using Landsat 8 Operational Land Imager (OLI) images. In total 99 Landsat 8 images were matched with turbidity data monitored in the reservoir between 2014 and 2022 with a time difference of at most 20 minutes. Estimation models were developed using regression analysis, multivariate adaptive regression splines (MARS), and TreeNet gradient boosting machine (TreeNet) methods. The success of the models was compared with the performance statistics of mean squared error, root mean squared error, mean absolute error, and Nash-Sutcliffe (NS) efficiency coefficient. The MARS and TreeNet methods were found to have equal predictive ability for the test dataset (NS = 0.61). The most significant parameter was determined as B4/B1 (red/coastal aerosol) with the MARS method, while B4/B2 (red/blue) was determined with the TreeNet model.

Keywords

Turbidity, Cheney reservoir, Landsat 8 OLI, Regression analysis

Landsat 8 Görüntüleri ile Cheney Rezervuarında Bulanıklık Tahmini: Regresyon, MARS ve TreeNet Yöntemlerinin Karşılaştırılması

Abstract

Rezervuarlardaki su kalitesi takibi, suyun kullanım amacına uygunluğu ve su canlılarının korunması için önemlidir ve su kalitesinin belirlenmesinde en yaygın kullanılan değişkenlerden biri de bulanıklıktır. Bu değişkenin takibinde kullanılan geleneksel yöntemlerin maliyetli ve zaman alıcı olması, su kalitesi takibi için daha ekonomik ve hızlı bir alternatif olan uzaktan algılama çalışmalarını ön plana çıkarmıştır. Bu çalışmada, Landsat 8 Operational Land Imager (OLI) görüntüleri kullanılarak Cheney Rezervuarında (Kansas, ABD) bulanıklık değişkenini tahmin edebilecek bir model kurulması amaçlanmıştır. Bu amaçla 99 Landsat 8 OLI görüntüsü, 2014-2022 yılları arasında rezervuarda takibi yapılan bulanıklık verileriyle aralarındaki zaman farkı 20 dakikadan az olacak şekilde eşleştirilmiştir. Tahmin modellerinin kurulmasında regresyon analizi, çok değişkenli uyarlanabilir regresyon eğrileri (MARS) ve TreeNet gradyan arttırma makinesi (TreeNet) yöntemleri kullanılmıştır. Kurulan modellerin performansları, ortalama karesel hata, ortalama karesel hatanın karekökü, ortalama mutlak hata ve Nash-Sutcliffe (NS) verimlilik katsayısı performans istatistikleri ile kıyaslanmıştır. MARS ve TreeNet yöntemlerinin tahmin gücünün test veri seti için birbirine eşit olduğu görülmüştür (NS = 0.61). En önemli parametrenin MARS yöntemi kullanılarak oluşturulan modelde B4/B1 (kırmızı/kıyı aerosol), TreeNet yöntemiyle oluşturulan modelde ise B4/B2 (kırmızı/mavi) olduğu belirlenmiştir.

Keywords

Bulanıklık, Cheney rezervuarı, Landsat 8 OLI, Regresyon analizi

Thanks

Yazarlar, veri izleme, işleme ve yönetimi için USGS personeline ve NASA/USGS’ye ücretsiz olarak sağladıkları veriler için teşekkür ederler.

References

• Abdelmalik, K. W. (2018). Role of statistical remote sensing for inland water quality parameters prediction. The Egyptian Journal of Remote Sensing and Space Science, 21(2), 193-200.
• Abdul Wahid, A., & Arunbabu, E. (2022). Forecasting water quality using seasonal ARIMA model by integrating in-situ measurements and remote sensing techniques in Krishnagiri reservoir, India. Water Practice & Technology, 17(5), 1230-1252.
• Agapiou, A. (2020). Evaluation of Landsat 8 OLI/TIRS level-2 and Sentinel 2 level-1C fusion techniques intended for image segmentation of archaeological landscapes and proxies. Remote Sensing, 12(3), Article 579. https://doi.org/10.3390/rs12030579
• Al-Fahdawi, A. A., Rabee, A. M., & Al-Hirmizy, S. M. (2015). Water quality monitoring of Al-Habbaniyah Lake using remote sensing and in situ measurements. Environmental Monitoring and Assessment, 187, 1-11.
• Alparslan, E., Aydöner, C., Tufekci, V., & Tüfekci, H. (2007). Water quality assessment at Ömerli Dam using remote sensing techniques. Environmental Monitoring and Assessment, 135, 391-398.
• Batur, E. (2019). Uzaktan algılama verilerinden su kalitesi parametrelerinin tespit edilmesi [Doktora tezi, İstanbul Teknik Üniversitesi]. YÖK Ulusal Tez Merkezi. https://tez.yok.gov.tr/UlusalTezMerkezi
• Bonansea, M., Ledesma, M., Rodriguez, C., & Pinotti, L. (2018). Using new remote sensing satellites for assessing water quality in a reservoir. Hydrological Sciences Journal, 64(1), 34-44.
• Boyd, C. E. (2019). Water quality: an introduction. Springer Nature.
• Christensen, V. G., Graham, J. L., Milligan, C. R., Pope, L. M., & Ziegler, A. C. (2006). Water quality and relation to taste-and-odor compounds in the North Fork Ninnescah River and Cheney Reservoir, South-central Kansas, 1997-2003. U. S. Geological Survey.
• Chu, H. J., He, Y. C., Chusnah, W. N. U., Jaelani, L. M., & Chang, C. H. (2021). Multi-reservoir water quality mapping from remote sensing using spatial regression. Sustainability, 13(11), Article 6416. https://doi.org/10.3390/su13116416
• Çölkesen, İ. (2015). Yüksek çözünürlüklü uydu görüntüleri kullanarak benzer spektral özelliklere sahip doğal nesnelerin ayırt edilmesine yönelik bir metodoloji geliştirme [Doktora tezi, İstanbul Teknik Üniversitesi]. YÖK Ulusal Tez Merkezi. https://tez.yok.gov.tr/UlusalTezMerkezi
• De Roos, A. J., Gurian, P. L., Robinson, L. F., Rai, A., Zakeri, I., & Kondo, M. C. (2017). Review of epidemiological studies of drinking-water turbidity in relation to acute gastrointestinal illness. Environmental Health Perspectives, 125(8), Article 086003. https://doi.org/10.1289/ehp1090
• Dilmen, Ö. (2023). Landsat 8 ve Sentinel 2 uydu görüntüleri ile içme suyu baraj göllerinde bulanıklık tahmini [Yüksek lisans tezi, Karadeniz Teknik Üniversitesi]. YÖK Ulusal Tez Merkezi. https://tez.yok.gov.tr/UlusalTezMerkezi
• Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189-1232.
• Friedman, J. H. (1991). Multivariate adaptive regression splines. Annals of Statistics, 19(1), 1-67.
• Gholizadeh, M. H., Melesse, A. M., & Reddi, L. (2016). A comprehensive review on water quality parameters estimation using remote sensing techniques. Sensors, 16(8), Article 1298. https://doi.org/10.3390/s16081298
• Gonzalez-Marquez, L. C., Torres-Bejarano, F. M., Rodriguez-Cuevas, C., Torregroza-Espinosa, A. C., & Sandoval-Romero, J. A. (2018). Estimation of water quality parameters using Landsat 8 images: application to Playa Colorada Bay, Sinaloa, Mexico. Applied Geomatics, 10, 147-158.
• Hossain, A. A., Mathias, C., & Blanton, R. (2021). Remote sensing of turbidity in the Tennessee River using Landsat 8 satellite. Remote Sensing, 13(18), Article 3785. https://doi.org/10.3390/rs13183785
• Hossen, H., Mahmod, W. E., Negm, A., & Nakamura, T. (2022). Assessing water quality parameters in Burullus Lake using Sentinel-2 satellite images. Water Resources, 49(2), 321-331.
• Khalid, H. W., Khalil, R. M. Z., & Qureshi, M. A. (2021). Evaluating spectral indices for water bodies extraction in western Tibetan Plateau. The Egyptian Journal of Remote Sensing and Space Science, 24(3), 619-634.
• Liu, L. W., & Wang, Y. M. (2019). Modelling reservoir turbidity using Landsat 8 satellite imagery by gene expression programming. Water, 11(7), Article 1479. https://doi.org/10.3390/w11071479
• Mann, A. G., Tam, C. C., Higgins, C. D., & Rodrigues, L. C. (2007). The association between drinking water turbidity and gastrointestinal illness: a systematic review. BMC Public Health, 7(1), Article 256. https://doi.org/10.1186/1471-2458-7-256
• Meng, H., Zhang, J., & Zheng, Z. (2022). Retrieving inland reservoir water quality parameters using Landsat 8-9 OLI and Sentinel-2 MSI sensors with empirical multivariate regression. International Journal of Environmental Research and Public Health, 19(13), Article 7725. https://doi.org/10.3390/ijerph19137725
• Moore, G. K. (1980). Satellite remote sensing of water turbidity. Hydrological Sciences Journal, 25(4), 407-421.
• Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., & Veith, T. L. (2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50(3), 885-900.
• Mortula, M., Ali, T., Bachir, A., Elaksher, A., & Abouleish, M. (2020). Towards monitoring of nutrient pollution in coastal lake using remote sensing and regression analysis. Water, 12(7), Article 1954. https://doi.org/10.3390/w12071954
• Nacar, S., Mete, B., & Bayram, A. (2020a). Estimation of daily dissolved oxygen concentration for river water quality using conventional regression analysis, multivariate adaptive regression splines, and TreeNet techniques. Environmental Monitoring and Assessment, 192(12), Article 752. https://doi.org/10.1007/s10661-020-08649-9
• Nacar, S., Mete, B., & Bayram, A. (2020b). Günlük çözünmüş oksijen konsantrasyonunun çok değişkenli uyarlanabilir regresyon eğrileri ile tahmin edilmesi. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 25(3), 1479-1498.
• Nacar, S., Şan, M., Kankal, M., & Okkan, U. (2024). Innovative polygonal trend analysis (IPTA) in detecting the seasonal trend behavior of statistically downscaled precipitation for the Eastern Black Sea Basin of Turkey. Urban Water Journal, 21(4), 406-418.
• Pinto, C. T., Jing, X., & Leigh, L. (2020). Evaluation analysis of Landsat level-1 and level-2 data products using in situ measurements. Remote sensing, 12(16), Article 2597. https://doi.org/10.3390/rs12162597
• Pizani, F. M., Maillard, P., Ferreira, A. F., & de Amorim, C. C. (2020). Estimation of water quality in a reservoir from Sentinel-2 MSI and Landsat-8 OLI sensors. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 3, 401-408.
• Rodriguez-Lopez, L., Duran-Llacer, I., Gonzalez-Rodriguez, L., Cardenas, R., & Urrutia, R. (2021). Retrieving water turbidity in Araucanian lakes (South-central Chile) based on multispectral Landsat imagery. Remote Sensing, 13(16), Article 3133. https://doi.org/10.3390/rs13163133
• Sharaf El Din, E., Zhang, Y., & Suliman, A. (2017). Mapping concentrations of surface water quality parameters using a novel remote sensing and artificial intelligence framework. International Journal of Remote Sensing, 38(4), 1023-1042.
• Sharda, V. N., Prasher, S. O., Patel, R. M., Ojasvi, P. R., & Prakash, C. (2008). Performance of multivariate adaptive regression splines (MARS) in predicting runoff in mid-Himalayan micro-watersheds with limited data. Hydrological Sciences Journal, 53(6), 1165-1175.
• Sun, X., Zhang, Y., Shi, K., Zhang, Y., Li, N., Wang, W., Huang, X., & Qin, B. (2022). Monitoring water quality using proximal remote sensing technology. Science of the Total Environment, 803, Article 149805. https://doi.org/10.1016/j.scitotenv.2021.149805
• Surisetty, V. V. A. K., Sahay, A., Ramakrishnan, R., Samal, R. N., & Rajawat, A. S. (2018). Improved turbidity estimates in complex inland waters using combined NIR–SWIR atmospheric correction approach for Landsat 8 OLI data. International Journal of Remote Sensing, 39(21), 7463-7482.
• State of Kansas (2023, 6 Aralık). 2022 Certified Kansas Population by County. 6 Aralık 2023’te https://budget.kansas.gov/wp-content/uploads/2022_Kansas_Certified_Population_7-1-23.pdf adresinden alındı.
• Stone, M. L., Juracek, K. E., Graham, J. L., & Foster, G. M. (2015). Quantifying suspended sediment loads delivered to Cheney Reservoir, Kansas: Temporal patterns and management implications. Journal of Soil and Water Conservation, 70(2), 91-100.
• Şan, M., Nacar, S., Kankal, M., & Bayram, A. (2023). Daily precipitation performances of regression-based statistical downscaling models in a basin with mountain and semi-arid climates. Stochastic Environmental Research and Risk Assessment, 37(4), 1431-1455.
• Şan, M., Nacar, S., Kankal, M., & Bayram, A. (2024). Spatiotemporal analysis of transition probabilities of wet and dry days under SSPs scenarios in the semi-arid Susurluk Basin, Türkiye. Science of the Total Environment, 912, Article 168641. https://doi.org/10.1016/j.scitotenv.2023.168641
• Theologou, I., Patelaki, M., & Karantzalos, K. (2015). Can single empirical algorithms accurately predict inland shallow water quality status from high resolution, multi-sensor, multi-temporal satellite data? The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 40, 1511-1516.
• U.S. Geological Survey (2023, 6 Aralık). Turbidity data in Cheney reservoir. U.S. Geological Survey. 6 Aralık 2023’te https://waterdata.usgs.gov/nwis/uv?site_no=07144790&legacy=1 adresinden alındı.
• Wang, F., Qin, Z., Song, C., Tu, L., Karnieli, A., & Zhao, S. (2015). An improved mono-window algorithm for land surface temperature retrieval from Landsat 8 thermal infrared sensor data. Remote Sensing, 7(4), 4268-4289.
• Wang, L., Wu, C., Gu, X., Liu, H., Mei, G., & Zhang, W. (2020). Probabilistic stability analysis of earth dam slope under transient seepage using multivariate adaptive regression splines. Bulletin of Engineering Geology and the Environment, 79, 2763-2775.