There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

计量经济分析 = Econometric analysis

This presentation is a case study taken from the travel and holiday industry. Paxport/Multicom, based in UK and Sweden, have recently adopted a recommendation system for holiday accommodation bookings. Machine learning techniques such as Collaborative Filtering have been applied using Python (3.5.1), with Jupyter (4.0.6) as the main framework. Data scale and sparsity present significant challenges in the case study, and so the effectiveness of various techniques are described as well as the performance of Python-based libraries such as Python Data Analysis Library (Pandas), and Scikit-learn (built on NumPy, SciPy and matplotlib). The presentation is suitable for all levels of programmers.

Machine learning with Python

Despite great progress in simulating multiphysics problems using the numerical discretization of partial differential equations (PDEs), one still cannot seamlessly incorporate noisy data into existing algorithms, mesh generation remains complex, and high-dimensional problems governed by parameterized PDEs cannot be tackled. Moreover, solving inverse problems with hidden physics is often prohibitively expensive and requires different formulations and elaborate computer codes. Machine learning has emerged as a promising alternative, but training deep neural networks requires big data, not always available for scientific problems. Instead, such networks can be trained from additional information obtained by enforcing the physical laws (for example, at random points in the continuous space-time domain). Such physics-informed learning integrates (noisy) data and mathematical models, and implements them through neural networks or other kernel-based regression networks. Moreover, it may be possible to design specialized network architectures that automatically satisfy some of the physical invariants for better accuracy, faster training and improved generalization. Here, we review some of the prevailing trends in embedding physics into machine learning, present some of the current capabilities and limitations and discuss diverse applications of physics-informed learning both for forward and inverse problems, including discovering hidden physics and tackling high-dimensional problems. The rapidly developing field of physics-informed learning integrates data and mathematical models seamlessly, enabling accurate inference of realistic and high-dimensional multiphysics problems. This Review discusses the methodology and provides diverse examples and an outlook for further developments.

Physics-informed machine learning

Appliance Load Monitoring (ALM) is essential for energy management solutions, allowing them to obtain appliance-specific energy consumption statistics that can further be used to devise load scheduling strategies for optimal energy utilization. Fine-grained energy monitoring can be achieved by deploying smart power outlets on every device of interest; however it incurs extra hardware cost and installation complexity. Non-Intrusive Load Monitoring (NILM) is an attractive method for energy disaggregation, as it can discern devices from the aggregated data acquired from a single point of measurement. This paper provides a comprehensive overview of NILM system and its associated methods and techniques used for disaggregated energy sensing. We review the state-of-the art load signatures and disaggregation algorithms used for appliance recognition and highlight challenges and future research directions.

https://www.mdpi.com/1424-8220/12/12/16838/pdf

Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey

A computer system receives customer records listing customer attributes and an adoption status of the customer, such as whether the customer has enrolled in a particular energy efficiency program An initial set of patterns are identified among the customer records, such as according to a decision tree The initial set is pruned to obtain a set of patterns that meet minimum support and effectiveness and maximum overlap requirements The patterns are assigned to segments according to an optimization algorithm that seeks to maximize the minimum effectiveness of each segment, where the effectiveness indicates a number of customers matching the pattern of each segment that have positive adoption status The optimization algorithm may be a bisection algorithm that evaluates a linear-fractional integer program (LFIP-F) to iteratively approach an optimal distribution of patterns

Predictive segmentation of customers

In this paper, we present an analysis of urban form, defined as the spatial distribution of macroeconomic quantities that characterize a city such as population, built environment, and energy use. In particular, we develop a framework to study the question of “mismatch” between the spatial distribution of lighting levels observed in a city (which was previously shown to be a proxy for energy access and wealth levels) and that city’s population density and built area distribution. This allows us to rank cities globally by their ability to, intuitively, “match people with lighting/energy access”. For this, we develop and make available a derived dataset we call CityNet that is based on best-available open-source remote sensing data products for the world’s largest 30,000 cities. We first describe how cities may be grouped into a few classes by the scale magnitude of these key quantities. Then we introduce simple quantities to measure their spatial distributions such as the average radial profile, the discrepancy between the radial profile of population and that of other quantities, and the effort of transforming the distribution of a given quantity to match that of the population density. To compare a given city against its “peers”, we define a simple benchmark model of urban form. We use this model to rank cities by the relative magnitude of the lack of access to built and energy infrastructure. The key observation we make is that in many parts of the world, development (including built area density and energy access and use) does not follow the spatial population distribution.

The Dark Side of the Earth: Benchmarking Lighting Access for All Cities on Earth and the CityNet dataset

In our previous work [1] we show the effectiveness of learning based schemes to emulate numerical simulations. Specifically, we explore the use of GANs to model Snow Water Equivalent (SWE). In this work, we present further analysis of these results, with a model now trained on 30 years of SWE data compared to 10 years for the previous. First, we study the model outputs with station data and find the outputs to closely match the station data. Second, we study the uncertainty of the cGAN based results. We study the correlation between noise and the outputs generated. We hope these contributions can help the community leverage the power of these deep learning models for future works.

Adrian Albert

Papers

Predictive segmentation of customers

The Dark Side of the Earth: Benchmarking Lighting Access for All Cities on Earth and the CityNet dataset

Modeling Mountain Snowpack Dynamics with CGANS: A Validation Study