Predictive Power of Machine Learning for Optimizing Solar Water Heater Performance: The Potential Application of High-Throughput Screening

Table 4

Measured heat collection rates (MJ/m²) of the two novel designs. All the measurements were performed under the environmental conditions similar to those of the measurements for the previous database (Table 1). Reproduced with permission from Liu et al. [23].

	Day 1	Day 2	Day 3	Day 4	Average	Predicted	Error rate
Design A	11.38	11.26	11.34	11.29	11.32	11.47	1.35%
Design B	11.47	11.43	11.42	11.45	11.44	11.66	1.90%