Combining flux variance similarity partitioning with artificial neural networks to gap-fill measurements of net ecosystem production of a Pacific Northwest Douglas-fir stand

•A flux variance similarity partitioning method was developed as a gap-filling model.•Results were compared with three established gap-filling models.•Gap-filled 18-year mean NEP values were similar among the four models.•There were large differences in annual photosynthesis and respiration values among the four models.•Accounting for light inhibition of daytime respiration  in ecosystem models is critical.