Thalosang Tshireletso

Mr. Thalosang Tshireletso

University of Cape Town, Private Bag X3, Rondebosch 7701, South Africa
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 September 2024 in Journal of Civil Engineering and Urbanism
Verified
Journal Article
Closed access
Thalosang TshireletsoThalosang Tshireletso
Thalosang Tshireletso
PMPilate Moyo
Pilate Moyo
Ensuring dam safety requires a monitoring system that can predict deformations and detect anomalies in real-time. This study combines the forecasting capabilities of the Prophet model with the real-time anomaly detection of a Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) framework. The Prophet model analyses historical deformation data to forecast future deformations, enabling early issue identification. The GMM-HMM framework continuously monitors incoming data to detect deviations from predictions. Results shows that the GMM-HMM, with 10 components and a Mahalanobis distance threshold of 0.1, achieved a precision of 0.602, recall of 1.0, and F-1 score of 0.751, ensuring high sensitivity and accurate anomaly detection on. The GMM-HMM was then used to detect anomalies on Prophet forecasted radial deformations. Anomalies were detected on upper limit and lower limit deformations. This combined approach enhances dam safety by integrating predictive and real-time monitoring capabilities, offering a comprehensive early warning system for dam infrastructure.

20 January 2021 in Infrastructures
Verified
Journal Article
Open access
PDF file
Thalosang TshireletsoThalosang Tshireletso
Thalosang Tshireletso
PMPilate Moyo
Pilate Moyo
MKMatongo Kabani
Matongo Kabani
A nonparametric machine learning model was used to study the behaviour of the variables of a concrete arch dam: Roode Elsberg dam. The variables used were ambient temperature, water temperatures, and water level. Water temperature was measured using twelve thermometers; six thermometers were on each flank of the dam. The thermometers were placed in pairs on different levels: avg6 (avg6-R and avg6-L) and avg5 (avg5-R and avg5-L) were on level 47.43 m, avg4 (avg4-R and avg4-L) and avg3 (avg3-R and avg3-L) were on level 43.62 m, and avg2 (avg2-R and avg2-L) and avg1 (avg1-R and avg1-L) were on level 26.23 m. Four neural networks and four random forests were cross-validated to determine their best-performing hyperparameters with the water temperature data. Quantile random forest was the best performer at mtry 7 (Number of variables randomly sampled as candidates at each split) and RMSE (Root mean square error) of 0.0015, therefore it was used for making predictions. The predictions were made using two cases of water level: recorded water level and full dam steady-state at Representative Concentration Pathway (RCP) 4.5 (hot and cold model) and RCP 8.5 (hot and cold model). Ambient temperature increased on average by 1.6 °C for the period 2012–2053 when using recorded water level; this led to increases in water temperature of 0.9 °C, 0.8 °C, and 0.4 °C for avg6-R, avg3-R, and avg1-R, respectively, for the period 2012–2053. The same average temperature increase led to average increases of 0.7 °C for avg6-R, 0.6 °C for avg3-R, and 0.3 °C for avg1-R for a full dam steady-state for the period 2012–2053.

15 September 2024 in Journal of Civil Engineering and Urbanism
Verified
Journal Article
Closed access
Thalosang TshireletsoThalosang Tshireletso
Thalosang Tshireletso
YOYashon Ouma
Yashon Ouma
DMDitiro Benson Moalafhi
Ditiro Benson Moalafhi
GAGeorge Anderson
George Anderson
Accurate prediction of water levels (WL) is essential for various applications, from flood management to environmental monitoring. In this study, an enhanced approach to feature selection tailored for water level prediction models is presented. Our method integrates Mutual Information and Recursive Feature Elimination with Cross-Validation (RFECV), augmented by the Non-Dominated Sorting Genetic Algorithm II (NSGA-II), to systematically evaluate and refine subsets of features. Mutual Information facilitates the identification of relevant feature dependencies, while RFECV iteratively eliminates less informative features to optimize predictive accuracy. The inclusion of NSGA-II further enhances the selection process by considering multiple conflicting objectives simultaneously, such as maximizing R2 score and minimizing the number of selected features, RMSE, and MAE. Through extensive experimentation and validation on real-world datasets, we demonstrate the effectiveness of our hybrid feature selection approach in capturing intricate relationships within the data, leading to significantly improved predictive performance in water level prediction models.

8 August 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MBMeghdad Bagheri
Meghdad Bagheri
Thalosang TshireletsoThalosang Tshireletso
Thalosang Tshireletso
SGSeyed Ali Ghorashi
Seyed Ali Ghorashi
Geotechnical hazards such as landslides, subsidence, slope instability, and infrastructure deformation threaten rapidly urbanising and environmentally stressed regions worldwide, intensifying the need for scalable and intelligent monitoring systems capable of continuously observing complex Earth surface dynamics. Although multisensor remote sensing fusion has substantially expanded the observational capabilities of modern geotechnical monitoring through the integration of Synthetic Aperture Radar (SAR), optical imagery, Light Detection and Ranging (LiDAR), and environmental data, existing fusion pipelines remain subject to several well-documented constraints, including weak semantic alignment, limited temporal reasoning, and poor transferability across heterogeneous environmental conditions. This review synthesises the emerging transition from conventional sensor-centric fusion toward intelligent geospatial monitoring architectures centred on deep multimodal representation learning, transformer-based temporal reasoning, self-supervised learning, and geospatial foundation models. Particular emphasis is placed on how recent architectures are designed to better preserve coherent spatial, temporal, and contextual environmental relationships within unified latent representation spaces rather than through downstream handcrafted integration. The review further examines the growing role of multimodal transformers, masked autoencoders, contrastive learning, and large-scale geospatial foundation models in enabling scalable environmental reasoning, adaptive multimodal learning, and transferable geospatial intelligence across sensing modalities and geographic domains. Finally, remaining challenges involving uncertainty, explainability, computational scalability, and environmental generalisation are discussed alongside future research directions involving continual learning, physics-aware artificial intelligence, and autonomous geotechnical monitoring systems. Together, the reviewed literature suggests that multimodal Earth observation is evolving from passive environmental sensing toward adaptive geospatial intelligence systems capable of scalable hazard reasoning and autonomous environmental understanding.

23 September 2026 in Progress in Engineering Science
Verified
Journal Article
Open access
Thalosang TshireletsoThalosang Tshireletso
Thalosang Tshireletso
PMPilate Moyo
Pilate Moyo

11 August 2026 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Open access
Thalosang TshireletsoThalosang Tshireletso
Thalosang Tshireletso
MBMeghdad Bagheri
Meghdad Bagheri
SGSeyed Ali Ghorashi
Seyed Ali Ghorashi