We propose to use aerosol optical depth (AOD) measurements as an early warning system, to CUE on-site validation of the soiling station and any available meteorological (met) station data to…

60Hertz Inc. was awarded a $295,808 Project Grant from the National Oceanic and Atmospheric Administration under the Small Business Innovation Research Program to develop an early warning system for soiling on solar energy assets. The company will use aerosol optical depth measurements from GOES-R ABI and on-site data to cue validation of soiling station and meteorological station data. This aims to help solar service companies move from reactive to proactive maintenance by identifying in advance when particulate matter cleaning may be needed. 60Hertz will create algorithms and software tools fusing these public and private data sets with additional factors to hasten decision-making around cleaning or protecting renewable energy generation assets threatened by weather impacts. Machine learning will be applied to explore correlational and causal relationships in the data that could support the warning system. The work will be performed in Anchorage, Alaska and is scheduled for completion by February 28, 2023.

We propose to use aerosol optical depth (AOD) measurements as an early warning system, to CUE on-site validation of the soiling station and any available meteorological (met) station data to validate if a work order to clean deposited particulate matter is necessary. This would move from reactive maintenance often weeks delayed, to proactive maintenance getting ahead of the weather impact if possible. Through this research, we will develop a suite of algorithms and ultimately software tools, that fuse multiple public and private (goes-R ABI AOD, and local site met/soiling station) datasets with features like project economics, asset location, weather forecast, etc. To hasten solar service companys decision times with regard to cleaning and/or protecting renewable generation assets. Our approach is to fuse the data and then explore feature relationships (correlative, causal) in the data using machine learning pattern identification and relationship learning algorithms ALO