Logic Tensor Network Modeling of Community Land Model

• Published in: 2024 IEEE Opportunity Research Scholars Symposium (ORSS) pp. 97 - 100
• Main Authors: O'Hearn, Eoin, Wang, Dali, He, Hongsheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15-04-2024
• Subjects: Accuracy; Computational modeling; Data models; Earth; Earth System models; Logic; Logic Tensor Networks; Machine learning; Mathematical models; Root mean square; Tensors; Testing
• DOI: 10.1109/ORSS62274.2024.10697947

Logic Tensor Networks (LTNs) have been shown to be capable of many artificial intelligence tasks, regression being among them. Earth System Models (ESMs) present large opportunities and a need for computationally fast and inexpensive regression solutions. In an approach to the capabilities of this neurosymbolic framework, dozens of equations were modeled from the Community Land Model. Most LTN regression models were able to reach greater than 0.65 axiom satisfaction and falling below an accuracy of 0.779 using the Root Mean Square Error (RMSE). Having yielded positive results, the Logic Tensor Network framework may provide the speed and efficiency desired in ESMs and further consideration of LTNs is justified.