With a scientific foundation spanning multidisciplinary areas like Machine Learning, Deep Learning, Neural Networks, Computational Mathematics, and Optimization, my objective is to leverage these methodologies to tackle real-world challenges, providing effective and practical solutions. I've applied my expertise across diverse domains, ranging from data-driven weather forecasting, precipitation nowcasting, learning solutions to dynamical systems and brain decoding. My contributions have encompassed tasks like, nonlinear system identification, parameter estimation, image/video segmentation, learning from partially labeled streaming data, domain adaptation, transfer learning, as well as various forms of supervised, unsupervised and semi-supervised learning. Primarily, my focus has been on pioneering advanced deep machine learning models which hold immense potential for widespread application across sectors such as Weather, Climate, Energy, Health, Robotics, Neuroscience, and beyond.
Code and Datasets
The software found here comes with no warranty. It is available for non-commercial research purposes only under the GNU General Public License. However, not withstanding any provision of the GNU General Public License, the software may not be used for commercial purposes without explicit written permission.
E. Reulen, S. Mehrkanoon, “GA-SmaAt-GNet: Generative Adverserial Small Attention GNet for Extreme Precipitation Nowcasting”, [arXiv, Github].
L. Vatamany, S. Mehrkanoon, “GD-CAF: Graph Dual-stream Convolutional Attentntion Fusion For Weather Data Fusion Precipitation Nowcasting”, [arXiv, Github].
C. Kaparakis, S. Mehrkanoon, “WF-UNet: Weather Data Fusion using 3D-UNet for Precipitation Nowcasting”, Procedia Computer Science, vol 222, pp. 223-232, 2023. [Github].
OnurBilgin, ThomasVergutz, S. Mehrkanoon, “AA-TransUNet: Attention Augmented TransUNet for Nowcasting Tasks”, IEEE-IJCNN, 2022. [Github].
OnurBilgin, ThomasVergutz, S. Mehrkanoon, “GCN-FFNN: A Two-Stream Deep Model for Learning Solution to Partial Differential Equations ”, Neurocomputing 511, pp. 131-141, 2022. [Github].
D Aykas, S. Mehrkanoon, “Multistream Graph Attention Networks for Wind Speed Forecasting ”, IEEE-SSCI, 2021. [Github].
T. Stanczyk, S. Mehrkanoon, “Deep Graph Convolutional Networks for Wind Speed Prediction”, ESANN 2021, [Github, DATA]
J.G. Fernández, I.A. Abdellaoui , S. Mehrkanoon, “Deep coastal sea elements forecasting using UNet-based models ”, Knowledge-Based Systems, Vol 252, Sept 2022, 109445. [Github]
K. Trebing, S. Mehrkanoon, “SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture, Pattern Recognition Letters, Vol 145, May 2021, Pages 178-186. [Github]
S. Mehrkanoon, “Deep shared representation learning for weather elements forecasting ”, Knowledge-Based Systems, Vol 179, pp. 120-128,Sept 2019[pdf][dataset]
S. Mehrkanoon, J. A. K. Suykens, "Multi-Label Semi-Supervised Learning using Regularized Kernel Spectral Clustering'', in Proc. of International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada, Jul.2016, pp. 4009-4016. [PDF][Matlab Code]
S. Mehrkanoon, M. Agudelo, J. A. K. Suykens, "Incremental multi-class semi-supervised clustering regularized by Kalman filtering'', Neural Networks, Vol. 71, Aug.2015, pp. 88-104. [PDF][Datasets]
S. Mehrkanoon, X. Huang, J.A.K. Suykens, "Non-parallel support vector classifiers with different loss functions", Neurocomputing, Vol. 143, Nov.2014, pp. 294-301.[PDF][Matlab Code]
S. Mehrkanoon, T. Falck, J. A. K. Suykens, “Parameter estimation for time varying dynamical systems using least squares support vector machines,” In proc. of the 16th IFAC Symposium on System Identification (SYSID), Jul. 2012, Brussels, Belgium, pp. 1300-1305. [PDF][Matlab Code]
S. Mehrkanoon, J.A.K. Suykens, "Learning Solutions to Partial Differential Equations using LS-SVM'', Neurocomputing, Vol. 159, 105-116, 2015. [PDF][Github]
S. Mehrkanoon, J. A. K. Suykens, "LS-SVM approximate solution to linear time varying descriptor systems", Automatica, 48(10), 2502-2511, 2012. [PDF][Code]
S. Mehrkanoon, T. Falck, J. A. K. Suykens, "Approximate solutions to ordinary differential equations using least squares support vector machines", IEEE Trans. Neural Netw. Learning Syst, 23(9), 1356-1367, 2012. [PDF][Github]
S. Mehrkanoon, "A direct variable step block multistep method for solving general third-order ODEs", Numerical Algorithms, 57(1), 53-66, 2011. [PDF][C Code]