Not Every Anomaly Tells the Same Story
The Challenge
Following storm-related damage at the 342 MW Solar PV Plant,
Datasee.AI was engaged to assess the site's condition and identify
modules requiring further investigation. Spanning approximately
950 acres with an installed capacity of 342 MWp, the site
presented the challenge of systematically assessing potential
damage across a large-scale solar installation.
The task went beyond identifying anomalies. Understanding the
condition of affected modules and connecting observations to their
precise locations was essential to support further investigation
and prioritise follow-up actions.
Our Solution
Datasee.AI conducted a drone-based thermal inspection of the solar
plant in July 2026. The inspection identified potential module
defects and abnormal thermal patterns, with findings categorised
and linked to location-specific references across the site.
By combining aerial inspection data with module-level
identification, Datasee.AI provided a structured view of the
reported conditions, helping the site team locate observations and
plan further assessments.
342 MWp
Installed solar capacity inspected
~950 acres
Plant area
6 days
Inspection period
39,945*
Number of Defected Modules
Impact
From Damage Assessment to Risk Prevention
The inspection provided location-specific information about reported module conditions, including panel failures, broken glass, hotspots, dirt, and diode-related issues. These findings supported a more targeted approach to investigating potential damage and planning follow-up assessments.
However, the incident also raises a broader question: Could better site planning and construction monitoring help reduce certain risks before a solar plant becomes operational?
What If Risk Assessment Began Earlier?
Had Datasee.AI's wider geospatial and engineering solutions been incorporated during the development of the 342 MW Solar PV Plant, they could have helped identify and address certain site-related vulnerabilities before construction was completed.
Topographic Survey and Hydrology Analysis:
Understanding terrain, slopes, and drainage pathways could have
informed site planning and helped identify areas requiring closer
assessment for runoff and water accumulation.
Grading and Cut-and-Fill Assessment:
Terrain modelling could have supported more suitable grading and
earthwork decisions based on site conditions.
Construction Progress Monitoring (CPM):
Monitoring construction against planned layouts and design
requirements could have helped identify deviations requiring
corrective action.
Construction Quality Monitoring (CQM):
Documenting visible construction issues and verifying work against
applicable quality requirements could have supported better
construction oversight.
These measures cannot guarantee protection against severe storms. However, when applied appropriately, they can help project teams identify and address certain preventable site-planning, drainage, grading, and construction-quality risks that may influence infrastructure performance during adverse weather.
The Datasee.AI Advantage
At Datasee.AI, our role extends beyond identifying issues after they occur. We bring together geospatial intelligence, engineering assessment, construction monitoring, and drone-based inspection to help renewable energy developers make informed decisions throughout the project lifecycle.
From understanding the terrain before construction to identifying anomalies during operations, better site intelligence can help teams move from reactive assessment towards proactive risk management.