Technology readiness levels for machine learning systems.

The development and deployment of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. Lack of diligence can lead to technical debt, scope creep and misaligned objectives, model misuse and failures, and expensive consequences. Engineering systems, on the other hand, follow well-defined processes and testing standards to streamline development for high-quality, reliable results. The extreme is spacecraft systems, with mission critical measures and robustness throughout the process. Drawing on experience in both spacecraft engineering and machine learning (research through product across domain areas), we've developed a proven systems engineering approach for machine learning and artificial intelligence: the Machine Learning Technology Readiness Levels framework defines a principled process to ensure robust, reliable, and responsible systems while being streamlined for machine learning workflows, including key distinctions from traditional software engineering, and a lingua franca for people across teams and organizations to work collaboratively on machine learning and artificial intelligence technologies. Here we describe the framework and elucidate with use-cases from physics research to computer vision apps to medical diagnostics.

Convcast: An embedded convolutional LSTM based architecture for precipitation nowcasting using satellite data.

Nowcasting of precipitation is a difficult spatiotemporal task because of the non-uniform characterization of meteorological structures over time. Recently, convolutional LSTM has been shown to be successful in solving various complex spatiotemporal based problems. In this research, we propose a novel precipitation nowcasting architecture 'Convcast' to predict various short-term precipitation events using satellite data. We train Convcast with ten consecutive NASA's IMERG precipitation data sets each at intervals of 30 minutes. We use the trained neural network model to predict the eleventh precipitation data of the corresponding ten precipitation sequence. Subsequently, the predicted precipitation data are used iteratively for precipitation nowcasting of up to 150 minutes lead time. Convcast achieves an overall accuracy of 0.93 with an RMSE of 0.805 mm/h for 30 minutes lead time, and an overall accuracy of 0.87 with an RMSE of 1.389 mm/h for 150 minutes lead time. Experiments on the test dataset demonstrate that Convcast consistently outperforms other state-of-the-art optical flow based nowcasting algorithms. Results from this research can be used for nowcasting of weather events from satellite data as well as for future on-board processing of precipitation data.

Big Data Challenges in Climate Science.

The knowledge we gain from research in climate science depends on the generation, dissemination, and analysis of high-quality data. This work comprises technical practice as well as social practice, both of which are distinguished by their massive scale and global reach. As a result, the amount of data involved in climate research is growing at an unprecedented rate. Climate model intercomparison (CMIP) experiments, the integration of observational data and climate reanalysis data with climate model outputs, as seen in the Obs4MIPs, Ana4MIPs, and CREATE-IP activities, and the collaborative work of the Intergovernmental Panel on Climate Change (IPCC) provide examples of the types of activities that increasingly require an improved cyberinfrastructure for dealing with large amounts of critical scientific data. This paper provides an overview of some of climate science's big data problems and the technical solutions being developed to advance data publication, climate analytics as a service, and interoperability within the Earth System Grid Federation (ESGF), the primary cyberinfrastructure currently supporting global climate research activities.

Bioinformatics: biomarkers of early detection.

Capturing, sharing, and publishing cancer biomarker research data are all fundamental challenges of enabling new opportunities to research and understand scientific data. Informatics experts from the National Cancer Institute's (NCI) Early Detection Research Network (EDRN) have pioneered a principled informatics infrastructure to capture and disseminate data from biomarker validation studies, in effect, providing a national-scale, real-world successful example of how to address these challenges. EDRN is a distributed, collaborative network and it requires its infrastructure to support research across cancer research institutions and across their individual laboratories. The EDRN informatics infrastructure is also referred to as the EDRN Knowledge Environment, or EKE. EKE connects information about biomarkers, studies, specimens and resulting scientific data, allowing users to search, download and compare each of these disparate sources of cancer research information. EKE's data is enriched by providing annotations that describe the research results (biomarkers, protocols, studies) and that link the research results to the captured information within EDRN (raw instrument datasets, specimens, etc.). In addition EKE provides external links to public resources related to the research results and captured data. EKE has leveraged and reused data management software technologies originally developed for planetary and earth science research results and has infused those capabilities into biomarker research. This paper will describe the EDRN Knowledge Environment, its deployment to the EDRN enterprise, and how a number of these challenges have been addressed through the capture and curation of biomarker data results.