TY - GEN
T1 - Explainability of Machine Learning Models for Hydrological Time Series Forecasting
T2 - 2023 International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023
AU - Querales, Marvin
AU - Salas, Rodrigo
AU - Torres, Romina
AU - Aguilera, Ana
AU - Morales, Yerel
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - This research evaluates the explainability of rules obtained in Neuro-Fuzzy (NF) models in hydrological time series forecasting. Thus, three NF models (Adaptive Network-based Fuzzy Inference System (ANFIS) and two versions of the Self-Identification Neuro-Fuzzy Inference Model (SINFIM)) were developed, considering the rain-runoff modeling as a particular case. The ANFIS model had the lowest performance, with many fuzzy rules challenging to interpret. The SINFIM 01 model performed best, but not all fuzzy rules were well explained. However, the SINFIM 02 model had a lower performance than the SINFIM 01 model but with more explainable fuzzy rules. With the examples developed, it is highlighted that within the NF models, it is necessary to focus on their performance during the forecast and look for a trade-off with explainability, thus taking advantage of their characteristic of more transparency than the black-box models.
AB - This research evaluates the explainability of rules obtained in Neuro-Fuzzy (NF) models in hydrological time series forecasting. Thus, three NF models (Adaptive Network-based Fuzzy Inference System (ANFIS) and two versions of the Self-Identification Neuro-Fuzzy Inference Model (SINFIM)) were developed, considering the rain-runoff modeling as a particular case. The ANFIS model had the lowest performance, with many fuzzy rules challenging to interpret. The SINFIM 01 model performed best, but not all fuzzy rules were well explained. However, the SINFIM 02 model had a lower performance than the SINFIM 01 model but with more explainable fuzzy rules. With the examples developed, it is highlighted that within the NF models, it is necessary to focus on their performance during the forecast and look for a trade-off with explainability, thus taking advantage of their characteristic of more transparency than the black-box models.
KW - Explainable Machine Learning
KW - Hydrological time series forecasting
KW - Neuro-Fuzzy models
UR - http://www.scopus.com/inward/record.url?scp=85174028281&partnerID=8YFLogxK
U2 - 10.1109/ICECCME57830.2023.10252284
DO - 10.1109/ICECCME57830.2023.10252284
M3 - Conference contribution
AN - SCOPUS:85174028281
T3 - International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023
BT - International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 July 2023 through 21 July 2023
ER -