Maximizing the Potential of Artificial Intelligence to Perform Evaluations in Ungauged Washbowls
DOI:
https://doi.org/10.18034/ei.v8i2.636Keywords:
Artificial Intelligence, LSTM, Machine Learning, Ungauged WashbowlsAbstract
Long short-term memory networks (LSTM) offer precision in the prediction that has never been seen before in ungauged basins. Using k-fold validation, we trained and evaluated several LSTMs in this study on 531 basins from the CAMELS data set. This allowed us to make predictions in basins for which we did not have any training data. The implication is that there is usually sufficient information in available catchment attributes data about similarities and differences between catchment-level rainfall-runoff behaviors to generate out-of-sample simulations that are generally more accurate than current models when operating under ideal (i.e., calibrated) conditions, i.e., when using under idealized conditions. In other words, existing models are generally less accurate when working under idealized conditions than out-of-sample simulations. We found evidence that including physical limits in LSTM models improves simulations, which we believe should be the primary focus of future research on physics-guided artificial intelligence. Putting in place additional physical constraints on the LSTM models.
Downloads
References
Achar, S. (2016). Software as a Service (SaaS) as Cloud Computing: Security and Risk vs. Technological Complexity. Engineering International, 4(2), 79–88. https://doi.org/10.18034/ei.v4i2.633 DOI: https://doi.org/10.18034/ei.v4i2.633
Achar, S. (2017). Asthma Patients’ Cloud-Based Health Tracking and Monitoring System in Designed Flashpoint. Malaysian Journal of Medical and Biological Research, 4(2), 159-166. https://doi.org/10.18034/mjmbr.v4i2.648 DOI: https://doi.org/10.18034/mjmbr.v4i2.648
Achar, S. (2018). Security of Accounting Data in Cloud Computing: A Conceptual Review. Asian Accounting and Auditing Advancement, 9(1), 60–72. https://4ajournal.com/article/view/70
Achar, S. (2019). Early Consequences Regarding the Impact of Artificial Intelligence on International Trade. American Journal of Trade and Policy, 6(3), 119-126. https://doi.org/10.18034/ajtp.v6i3.634 DOI: https://doi.org/10.18034/ajtp.v6i3.634
Addor, N., Newman, A., Mizukami, N., & Clark, M. P. (2017). Catchment attributes for large-sample studies. https://doi.org/10.5065/D6G73C3Q DOI: https://doi.org/10.5065/D6G73C3Q
Chen, S., Deming, C., & Adusumalli, H. P. (2018). Safety Assessment of IoT: Warning Scan for Security. 技术与管理回顾, 1(1), 1–6. Retrieved from https://xn--jhqs8sh4jbvevnt0xk4h3c.xn--6frz82g/index.php/tmr/article/view/1
Fadziso, T., Adusumalli, H. P., & Pasupuleti, M. B. (2018). Cloud of Things and Interworking IoT Platform: Strategy and Execution Overviews. Asian Journal of Applied Science and Engineering, 7, 85–92. Retrieved from https://upright.pub/index.php/ajase/article/view/63
Ganapathy, A. (2018). Cascading Cache Layer in Content Management System. Asian Business Review, 8(3), 177-182. https://doi.org/10.18034/abr.v8i3.542 DOI: https://doi.org/10.18034/abr.v8i3.542
Pasupuleti, M. B., & Adusumalli, H. P. (2018). Digital Transformation of the High-Technology Manufacturing: An Overview of Main Blockades. American Journal of Trade and Policy, 5(3), 139-142. https://doi.org/10.18034/ajtp.v5i3.599
Pasupuleti, M. B., Miah, M. S., & Adusumalli, H. P. (2019). IoT for Future Technology Augmentation: A Radical Approach. Engineering International, 7(2), 105-116. https://doi.org/10.18034/ei.v7i2.601
Rahman, M. M., Pasupuleti, M. B., & Adusumalli, H. P. (2019). Advanced Metering Infrastructure Data: Overviews for the Big Data Framework. ABC Research Alert, 7(3), 159-168. https://doi.org/10.18034/abcra.v7i3.602
--0--
Downloads
Published
Issue
Section
License
Engineering International is an Open Access journal. Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a CC BY-NC 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of their work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal. We require authors to inform us of any instances of re-publication.
