- Identify the part of your data that overlaps with Nearmap AI data. For example, the presence of solar panels at an address.
- Identify a common key on which to merge the data sets (such as a parcel identifier or address centroid), and merge them.
Filter for the cases where there's a mismatch between your data and ours.
- If they are well matched on date and definition, this may only be a lower percentage of cases.
- If there is an approximate match only, the level of mismatch may be much higher. (for example, your definition of construction is as soon as a DA is submitted, rather than commenced, or the data comes from different dates)
- Sort from highest to lowest confidence. Nearmap AI highest confidence results are most likely to be correct, and present opportunities for you to update your data set. Our lowest confidence results are most likely cases where your data is strong, and should be left unchanged.
- Look at various examples in MapBrowser as you work down the list, to determine a confidence cut off where you are comfortable overriding your data with ours.
Solar panels example
If a utility has a data set based on documented installs, there will be examples where the panels were removed (due to a knock-down rebuild or the paperwork was lost). These are likely to come up as high confidence results with Nearmap AI.
On the other hand, there are cases where the utility's data set is likely to be stronger, and lower confidence scores will be reported by Nearmap AI. T he Sydney Olympic village has many examples of very small solar arrays that were installed in the year 2000. These are likely to be well documented in the data set, but are visually challenging (the two-panel, 20+ year old arrays with a very wide bezel look very much like skylights). See the image below.
Low confidence results on houses in Sydney Olympic Village, with small 20 year-old solar arrays.
NOTE: While a workflow like the one described above can further enhance the value you get from Nearmap AI, it's important to ensure correct interpretation and a useful outcome, rather than a focus on where Nearmap AI “went wrong”.