The renewable energy industry has experienced significant growth worldwide, explained by the drop in the cost of its generation in the last decade. According to the International Renewable Energy Agency (IRENA), the transition into using clean energy could meet 90% of the goals of the Paris Agreement to reduce emissions from this industry. Argentina has great solar and wind potential to generate energy from these sources, which would allow the country to increasingly focus on its production. …

En los últimos tiempos, el cuidado del medioambiente ha cobrado una enorme relevancia, múltiples iniciativas a niveles globales y gubernamentales han activado programas de concientización y financiación de la temática. El objetivo es encontrar un punto óptimo para el máximo desarrollo humano con las mínimas implicancias de cambios en el medio ambiente.

En Dymaxion Labs hemos desarrollado una plataforma de monitoreo satelital denominada SatLomas para el sistema de Geolomas que se encuentra en Lima, Perú. El sistema Geolomas del Proyecto EbA Lomas busca promover condiciones para la conservación de estos ecosistemas únicos y frágiles que albergan gran biodiversidad de importancia global, y reducir los riesgos de su degradación. El proyecto de Conservación, gestión y rehabilitación de los ecosistemas frágiles en Lima-EbA Lomas es financiado por el GEF e implementado por el PNUD por mandato del Servicio Nacional e Areas Naturales Protegidas - SERNANP. …

Introduction

At Dymaxion Labs, we are developing a geospatial analytics platform (DYMAX). Our goal is to make scalable machine learning modeling with multispectral satellite imagery as the main input.

To achieve this we leverage the computing power of Google Cloud Platform. In particular, we use AutoML Vision, AutoML Tables, and Cloud ML.

We introduce you to a technical article, showcasing all the power of our platform and how we can apply to real-world examples like swimming pool detection in large areas. This article is about how to use the Dymaxion’s API to create an entire machine learning workflow programmatically.

Methodology

It’s a good idea to begin first describing our methodology. For data science projects like this one is very important how the user is going to define the problem (Where are the swimming pools in our area of interest?) and what datasets or ground truth information we can gather from the real world. …

We are pleased to announce today that Juan Pablo Villa (JP) has joined Dymaxion Labs as Chief Strategy Officer (CSO). JP has a Bs. in Computer Science from Universidad Nacional de La Plata with a major in the image processing field, counting with 2 successful exits in the Technology business space. Prior to this position, JP was the Founder and CEO of VMN+, a nearshore team augmentation company servicing Fortune 500 companies in 20 countries along US, Latam, and Europe.

“Getting back to the technology business with a global scale, the platform-based business model was one of my goals. During the last year, I’ve seen a lot of potential and exponential growth in the geospatial business intelligence field. Dymaxion Labs, backed by UNICEF Innovation fund, offers a set of innovative insights for the agriculture and urban verticals. Their platform combines satellite imagery, huge datasets from open and private domain, IoT real-time sensing and predictive models using machine learning algorithms. …

At Dymaxion Labs, we have been developing over the last years a methodology for mapping informal settlements in Latin America. As a part of the portfolio of companies of the UNICEF Innovation Fund, we have published the source code and our maps online. Now, we aim to track every single informal settlement around the world, proposing a transparent, low-cost, evidence-based, up-to-date platform. Using our platform, private companies and the public sector can achieve strategic data-driven decisions from their geospatial imagery targets.

Considering the dynamics of growth in the cities of low and lower middle income countries, understand this type of phenomenon is key to the future of our planet: 90% of this growth will take place in less developed regions such as Southeast Asia, Sub-Saharan Africa, and Latin America. The definition of peri-urban farming, according to FAO and the World Food Program, says that they are units close to town which operate intensive semi- or fully commercial farms to grow vegetables and other horticulture. …

Durante este año en Dymaxion Labs hemos estado trabajando junto con el Ministerio de Desarrollo Social (MIDES) en el desarrollo de herramientas para el procesamiento masivo de imágenes satelitales. El objetivo fue la producción de un modelo predictivo especializado de vulnerabilidades socioeconómicas, de riesgo social y de exposición a amenazas de origen natural, socio natural y antrópico.

Cabe destacar que en lo referido a vulnerabilidad social, el MIDES cuenta con un instrumento estadístico utilizado para focalizar los programas de transferencias no contributivas en el Uruguay, denominado Índice de Carencias Críticas (ICC). …

As already mentioned in our previous posts regarding mapping of slums using ConvNets and delineating roofs in non-residential areas, the combination of aerial imagery and machine learning provides many potential use cases beyond our initial work of mapping slums and informal settlements.

In the very beginning of Dymaxion, we needed to develop the core algorithms to sustain every block of the slums mapping project, like batch imagery processing, roof and green areas detection, and urban sprawling segmentation, among other tasks. Meeting different people interested in our technology beyond the scope of our project helped us validate some hypotheses related to other applications, like agriculture and civil engineering. …

As you could see in our latest post, we are working on automating the mapping of slums and informal settlements in Latin America through our open source tool AP-Latam. If governments had updated information about slums and their growth, they could give the affected families better life conditions and change their future. In this post we will talk about how we are dealing with segmentation of roof contours for each potential slum that our methodology detected.

To combine satellite imagery and machine learning algorithms, we fine-tuned a ResNet50 neural network and predicted which tiles contains an informal settlement. You can read more about this method in the aforementioned post. To get better results, we also used a vector dataset of blocks, and calculated the intersection between the squares and blocks. …