**7. Conclusions**

In this study, the surface soil moisture products of the GEE SMAP were modeled by SVM and ELM. The TLBO algorithm optimized these models to estimate future steps based on the forecast of each step. The results showed that the ELM model is only able to forecast 23 steps each time with R = 0.8313, RMSE = 6.1285, and MAE = 5.0021. The SVM model was only able to estimate the future steps one step ahead with R = 0.8406, RMSE = 18.022, and MAE = 17.9941. Both models' accuracy dropped significantly while forecasting longer periods than the ones mentioned. Since this study is a sequence to a former study on the same product of SMAP by TLBO-LSTM, a comparison between the results was made. Accordingly, the proposed deep learning LSTM method in the former study is more successful in forecasting longer periods than ELM and SVM, with R = 0.9337, RMSE = 1.7809, and MAE = 1.1892. We sugges<sup>t</sup> that advanced smoothing methods should be integrated, or other seasonal preprocessing techniques, to decrease both fluctuations and correlations in the time series structure.

**Author Contributions:** Conceptualization, H.B.; methodology, H.B. and M.Z.; software, M.Z.; validation, H.B. and M.Z.; formal analysis, M.Z.; investigation, M.Z.; resources, H.B.; data curation, M.Z.; writing—original draft preparation, M.Z.; writing—review and editing, H.B.; visualization, M.Z.; supervision, H.B.; project administration, H.B.; funding acquisition, H.B. and M.Z. All authors have read and agreed to the published version of the manuscript.

**Funding:** The authors acknowledge the financial support provided by Fonds de recherche du Québec—Nature et technologies (FRQNT) (#316369) and Natural Sciences and Engineering Research Council of Canada (NCERT) Discovery Grant (#RGPIN-2020-04583) to perform the current research.

**Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** The readers can find the dataset by the following GEE app [SOIL-PARAM] developed by [2]: Link to app: https://zemoh.users.earthengine.app/view/soilparam (accessed on 24 December 2022).

**Conflicts of Interest:** The authors declare no conflict of interest.
