TRANSCRIPT: (00:00)
Nina Jean Louis
Hi, my name is Nina Jean Louis. I am a structural engineer and I’m also a Ph.D. student at the University of Miami, studying how can we make our cultural landscapes resilient against climate change impacts. I was working very closely with an advisor that’s now my advisor on a community project about resiliency and climate resiliency and in the Little Haiti area.
 
(00:23)
Nina Jean Louis
And then I just really would like to continue that work and it just kind of all happened together and I got tired of the industry as well and wanted to basically see how we can further climate resilience in the academic space as well. So that’s how I got back there. While to really create innovative solutions worldwide, you can only pursue it through one thought medium.
 
(00:48)
Nina Jean Louis
You have to work with other disciplines because one discipline may be really strong and qualitative research, while the other can be really strong and quantitative. And both are needed together to create really impactful solutions that are also community driven. He’d say this by engineering. You know, we create a lot of amazing solutions, but the one thing the area that we lack is community participatory involvement.
 
(01:13)
Nina Jean Louis
And sometimes we think of that in the process a little later down the road when we’re thinking about solutions. So this is where when working with more social science and humanities that we get to now put community participatory thinking at the forefront, which is needed because we create actual climate solutions that are impactful for the community. It has to start with community and instead of actually just making them a plug in.
 
(01:37)
Nina Jean Louis
So it has to start with them. And as engineers, we may not know how to do that. So that’s why it’s so important to work interdisciplinary with other more social science humanities disciplines. I would say a lot of honestly, my most challenging have not been within the industry space. It’s been more in the volunteer it’s been in the more community based space because you get to really see the financial struggles of a lot of underrepresented communities go through and how difficult that is.
 
(02:06)
Nina Jean Louis
And so that really puts an impact on your solution moving forward. It’s not okay. Yeah, you have this structure that may be historic and yes, you may have some deteriorated roofing membranes or you may have some roofing joist that are deteriorated. But the cost to actually make that happen for underrepresented sites is something that we don’t see day to day on the usual day to day industry drawing calculations side.
 
(02:33)
Nina Jean Louis
And so I find that also to be challenging and then also understanding what the community values to. It’s we have to come in there blind. We have to not put our own, how should I say, like our own motives for it’s like we we do have to really walk in there, open minded and understanding exactly what the community needs and what the community wants.
 
(02:58)
Nina Jean Louis
And that process can be very challenging with most technology that can be very powerful, if used correctly. And also if you supervise as well, like when we sometimes think of AI, we really kind of go straight to the dystopic sci fi robot takeover. And no, that’s not not what we’re trying to do here. What we’re trying to do is essentially with the ethical considerations and the supervision by human agency, we want to be able to utilize the AI machine learning to help discover and create visibility for underrepresented sites that are not on municipal registers.
 
(03:35)
Nina Jean Louis
They’re not on state or national registers to give them that, to give those sites that light. And so this is where you also have to work with the community as well, because even though you may find these sites, they may find these sites, there’s a story behind those sites. And also to be able to portray this sites, we can’t commodify, then we can exploit them.
 
(03:57)
Nina Jean Louis
And sometimes AI has a tendency to do that because it doesn’t have that emotional thinking. And that’s why the community as a part of this process is so important. How we’re going to utilize it is the baseline process of, okay, it’s a human, or to walk through this process of saying going through archival historical documents, going through geological dating, to going through aerial imagery to find these sites, how would a human basically go step by step that will be like your testing or your training data?
 
(04:26)
Nina Jean Louis
And then we would utilize machine learning, which is a type of in machine learning and segmentation, which are different types of processes that I can generally basically generate. Utilize those to say, okay, let’s simulate this process and see if we can actually use that same side, that same training data to see if we can find that site. And once that process is said and done, we now get to repeat that again for other sites and also interfacing with a community say, Hey, we found this site.
 
(04:59)
Nina Jean Louis
What does this mean to you? Is this an important site to your community? And that’s kind of like the further validation of it currently right now. So with the chart testing that Marilyn said, we’re going to talk about a little bit more. We’re basically utilizing this technology in the vein of the saltwater railroad and seeing if we can find more sites that speak to that cultural landscape essentially.
 
(05:22)
Nina Jean Louis
And that is going to take there’s already sites that are already have been identified through charter initiatives. Currently chart has found, has known the bill bags park as we know, Egmont Key, and Fort DeSoto. But what other sites can we find that can speak to that history? So that’s that’s kind of the case study that we’re looking at currently.