Underpinning much of this is the costs associated with image capture and the lack of fine-grain temporal resolution. You can write software to analyze and pinpoint certain "things" the customer is looking for, but in all cases that analysis is a snapshot of a moment in time. Stringing along multiple snapshots helps paint a broader picture, but revisit rate is still a few times a day in the BEST case (and the customer likely has deep pockets if that's true). The bottleneck is image capture.
The satellite industry is an incredibly high-walled garden. Launch costs are falling and the use of off-the-shelf hardware combined with smaller satellite forms is improving revisit, but it's a steep hill to climb no less. Custom-built monitoring algos are subject to diminishing returns based on a variety of factors and the number of images in a data set is certainly part of that.
Agreed. I’m biased, but keep an eye on synthetic aperture radar. The physics of those systems allow for monitoring with a pretty different theoretical limit on price-per-revisit from their optical companions: https://joemorrison.substack.com/p/why-im-leaving-azavea-to-...
The satellite industry is an incredibly high-walled garden. Launch costs are falling and the use of off-the-shelf hardware combined with smaller satellite forms is improving revisit, but it's a steep hill to climb no less. Custom-built monitoring algos are subject to diminishing returns based on a variety of factors and the number of images in a data set is certainly part of that.