Comparing Supervised and Semi-supervised Machine Learning Methods for Mapping Aquatic Weeds, as Biomass Resource from High-Resolution UAV Images

被引：0

作者：

Clement Nyamekye ^{[1
]}

Linda Boamah Appiah ^{[2
]}

Richard Arthur ^{[3
]}

Gabriel Osei ^{[4
]}

Samuel Anim Ofosu ^{[1
]}

Samuel Kwofie ^{[5
]}

Benjamin Ghansah ^{[2
]}

Dieter Bryniok ^{[6
]}

机构：

[1] Department of Civil Engineering, Koforidua Technical University, P. O. Box KF981, Koforidua

[2] Department of Environmental Management and Technology, Koforidua Technical University, P. O. Box KF981, Koforidua

[3] Department of Energy Systems Engineering, Koforidua Technical University, P. O. Box KF981, Koforidua

[4] Department of Automotive Engineering, Koforidua Technical University, P. O. Box KF981, Koforidua

[5] Department of General Studies, Koforidua Technical, University, P. O. Box KF981, Koforidua

[6] Hamm-Lippstadt University of Applied Sciences, Marker Allee 76-78, Hamm

来源：

Remote Sensing in Earth Systems Sciences | 2024年 / 7卷 / 3期

关键词：

Aquatic weeds; Machine learning; Semi-supervised; Supervised; Unmanned aerial vehicle;

D O I：

10.1007/s41976-024-00119-x

中图分类号：

学科分类号：

摘要：

Detection and mapping are essential steps for resources assessment for biomasses such as aquatic weeds and are also important management steps aimed at curbing the ecological and socio-economic challenges posed by aquatic weeds on waterbodies. However, significant challenges exist in obtaining labeled data to perform supervised classification of aquatic weeds due to risk and cost involved in navigating over large waterbodies. This study assessed whether using semi-supervised learning (SSL) with fewer number of labeled aquatic weeds will be adequate for a machine learning (ML) model to produce high classification accuracy. A simultaneous collection of field samples of the aquatic weed species, mainly water hyacinth and submerged weeds for classification purposes. Image classifications with five ML algorithms (k nearest neighbor — kNN, decision tree — DT, gradient boosting — GB, random forest — RF, support vector machines — SVM) using both supervised and semi-supervised learning methods were performed. The results indicated that both SL and SSL produced high accuracies with F1 score between 0.8 and 0.91 and overall accuracy (OA) between 80 and 95%. It was therefore concluded that semi-supervised classification can equally produce satisfactory accuracy like a supervised classification, though the former has the advantage of using fewer labeled data, thereby reducing cost. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

引用

页码：206 / 217

页数：11

共 23 条

[1] Nyamekye C., Ofosu S.A., Arthur R., Osei G., Appiah L.B., Kwofie S., Ghansah B., Bryniok D., Evaluating the spatial and temporal variations of aquatic weeds (Biomass) on Lower Volta River using multi-sensor Landsat images and machine learning, Heliyon, 7, 5, (2021)
[2] Li G., Hu R., Wang N., Yang T., Xu F., Li J., Wu J., Huang Z., Pan M., Lyu T., Cultivation of microalgae in adjusted wastewater to enhance biofuel production and reduce environmental impact: pyrolysis performances and life cycle assessment, J Clean Prod, 355, (2022)
[3] Almarashi J.Q.M., El-Zohary S.E., Ellabban M.A., Abomohra A.E.-F., Enhancement olipid production and energy recovery from the green microalga Chlorella vulgaris by inoculum pretreatment with low-dose cold atmospheric pressure plasma (CAPP), Energy Convers Manag, 204, (2020)
[4] Thamaga K.H., Dube T., Remote sensing of invasive water hyacinth (Eichhornia crassipes): a review on applications and challenges, Remote Sens Appl Soc Environ, 10, pp. 36-46, (2018)
[5] Pabi O., Akpabey F.J., High spatial resolution mapping and management options of aquatic weeds at the lower volta, Dams Development Downstream Communities, (2017)
[6] Pereira L.A., Nakamura R.Y., De Souza G.F., Martins D., Papa J.P., Aquatic weed automatic classification using machine learning techniques, Comput Electron Agric, 87, pp. 56-63, (2012)
[7] Mukarugwiro J.A., Newete S.W., Adam E., Nsanganwimana F., Abutaleb K., Byrne M.J., Mapping spatio-temporal variations in water hyacinth (Eichhornia crassipes) coverage on Rwandan water bodies using multispectral imageries, Int J Environ Sci Technol, 18, 2, pp. 275-286, (2021)
[8] Al-Azzam N., Shatnawi I., Comparing supervised and semi-supervised machine learning models on diagnosing breast cancer, Ann Med Surg, 62, pp. 53-64, (2021)
[9] Chen F., Wang L., Gu Q., Wang M., Ding X., Nexus between natural resources, financial development, green innovation and environmental sustainability in China: Fresh insight from novel quantile ARDL, Resour Policy, 79, (2022)
[10] Ligthart A., Catal C., Tekinerdogan B., Analyzing the effectiveness of semi-supervised learning approaches for opinion spam classification, Appl Soft Comput, 101, (2021)

← 1 2 3 →