Predicting indoor air temperature and thermal comfort in occupational settings using weather forecasts, indoor sensors, and artificial neural networks

We present an approach to generate location-specific forecasts of indoor temperature (Ti) and thermal comfort and issue indoor heat warnings for occupational settings. Indoor forecasts are generated using standard outdoor weather forecasting products and an artificial neural network (ANN) trained on-site using local indoor mea-surements from a low-cost sensor system measuring Ti and indoor physiologically equivalent temperature (PETi). The outcomes are hourly indoor Ti and PETi forecasts. Different ANN-based forecast products using different predictors were concurrently tested at 121 workplaces in agricultural, industrial, storage, and office buildings using data for an entire annual cycle. A forecast was considered skillful when the Ti and PETi forecast was <2 K from actual measurements. The best-performing model used the predictors time of year, week, and day; solar position; and outdoor weather forecast variables to train and run an ANN to predict Ti or PETi. It had an annual average mean absolute forecast error of 0.87 K for Ti and 0.99 K for PETi over the next 24 h, with Pearson correlation coefficients of 0.98 and 0.97, respectively. Overall, 91% of Ti forecasts and 88% of PETi forecasts were skillful. Indoor forecasts showed larger errors in the summer than in the winter. We conclude that combining indoor data with weather forecasts using ANNs could be implemented widely to provide location-specific indoor weather forecasts to improve and localize heat and health warning systems.

Automated summary

We propose a method to generate location-specific forecasts of indoor temperature and thermal comfort using an artificial neural network trained on-site with local indoor measurements. The forecasts combine standard outdoor weather forecasting products with low-cost sensor system data. The best-performing model had an average mean absolute forecast error of 0.87 K for temperature and 0.99 K for physiological equivalent temperature over the next 24 hours, with high Pearson correlation coefficients. Overall, 91% of temperature forecasts and 88% of physiological equivalent temperature forecasts were skillful. This approach could be widely implemented to improve and localize heat and health warning systems.