**5. Conclusions**

Feed-forward neural networks were used in this study to model urban temperature time series from experimental data. The aim was to explore the reliability of these models in the context of low data availability, as well as the potential benefits from targeting the UHI intensity with these models. Results showed that, for the case study of Madrid, the training dataset could be reduced to 9 or even 6 months without compromising too much the accuracy of the FNN models, particularly when using the UHII approach (2.4% and 6.2% increase in RMSE, respectively).

Results showed that the UHII approach generally outperformed the TEMP approach. Overall, UHII models converged to lower error ratios with a smaller number of neurons, proving to be more effective at predicting the urban temperature of a reference site. When using the exact same configuration and structure, UHII models exhibited a significant increase in performance. TEMP models appeared to be quite seasonally dependent, thus facing more problems for modelling temperatures outside the training months. This was particularly relevant when trained on just 3 months of data, when the accuracy differences between UHII and TEMP models was at their highest. We argue that this could be related to the annual cyclical behaviour of temperatures. Targeting the UHI intensity with the FNNs instead, which in Madrid has shown to be almost stationary, seems to reduce uncertainty when modelling temperatures from a relatively small dataset.

The potential use of smaller datasets for training FNNs and still obtaining reliable results might benefit urban climate researchers since field measurements could be reduced in time and costs. Researchers might also take advantage of the accurate preliminary results that can be generated with relatively small datasets for speeding up their research, or for extending their measurements to other urban areas.

**Author Contributions:** Conceptualization, M.N.-P., A.M. and P.S.; methodology, M.N.-P., A.M. and P.S.; software, M.N.-P. and P.S.; validation, M.N.-P., A.M. and P.S.; formal analysis, M.N.-P., A.M. an P.S.; investigation, M.N.-P.; resources, M.N.-P. and C.S.-G.S.; data curation, M.N.-P.; writing—original draft preparation, M.N.-P., A.M., P.S. and C.S.-G.S.; writing—review and editing, M.N.-P., A.M., P.S., C.S.-G.S. and F.J.N.G.; visualization, M.N.-P.; supervision, A.M. and P.S.; project administration, M.N.-P., C.S.-G.S. and F.J.N.G.; funding acquisition, M.N.-P., C.S.-G.S. and F.J.N.G. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was funded by an FPU research gran<sup>t</sup> (FPU15/05052) and by a research visit gran<sup>t</sup> (EST17/00825), both from the Spanish Ministry of Education, Culture and Sport. This research was also supported by the MODIFICA research project (BIA2013-41732-R), funded by the Spanish Ministry of Economy and Competitiveness.

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

**Informed Consent Statement:** Not applicable.

**Acknowledgments:** The authors would like to thank the Spanish National Meteorological Agency (AEMET) for providing access to their meteorological data, and Luis Tejero Encinas and Juan Azcárate Luxán, from the Madrid City Council' Subdivision of Energy and Climate Change, for their support with the urban measurements.

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