Spatiotemporal Modeling of Real World Backsheets Field Survey Data: Hierarchical (Multilevel) Generalized Additive Models

Raymond Wieser, Zelin (Zack) Li, Stephanie Moffitt, Ruben Zabalza, Evan Boucher, Silvana Ayala, Matthew Brown, Xiaohong Gu, Liang Ji, Colleen O'Brien, Adam Hauser, Greg O'Brien, Xuanji Yu, Roger French, Michael Kempe, Jared Tracy, Kausik Choudhury, William Gambogi, Laura Bruckman, Kenneth Boyce

Research output: Contribution to conferencePaperpeer-review

2 Scopus Citations


Assessing photovoltaic module backsheet durability is critical to increasing module lifetime. Laboratory-based accelerating testing has recently failed to predict large scale failures of widely adopted polymeric materials. Additionally, there is a growing concern on characterizing the non-uniformity of field exposure. Therefore, data from field surveys are critical to assess the performance of component lifetimes. Using a documented field survey protocol, 19 field surveys were conducted. The focus of this survey strategy is to investigate spatial continuity in degradation modes. By combining field survey data with real-time satellite weather data, stressor / response models have been trained. Generalized additive Models (GAM) model was created to predict the value of degradation based on measured predictors. Two different GAM constructions were testing using different implementations of basis splines. The model includes variables on the environmental stressors of the system and the location of each measurement in the PV mounting structure. The incorporation of hierarchical structure into the models allowed for material specific degradation rates, while maintaining the assumption of a global trend. The model performed well with an adjusted R {2} of 0.975 for yellowness index prediction.

Original languageAmerican English
Number of pages6
StatePublished - 2022
Event49th IEEE Photovoltaics Specialists Conference, PVSC 2022 - Philadelphia, United States
Duration: 5 Jun 202210 Jun 2022


Conference49th IEEE Photovoltaics Specialists Conference, PVSC 2022
Country/TerritoryUnited States

Bibliographical note

See NREL/CP-5K00-81961 for preprint

NREL Publication Number

  • NREL/CP-5K00-85098


  • Backsheet
  • Degradation
  • Field Survey
  • Modeling
  • Spatio-temporal


Dive into the research topics of 'Spatiotemporal Modeling of Real World Backsheets Field Survey Data: Hierarchical (Multilevel) Generalized Additive Models'. Together they form a unique fingerprint.

Cite this