Yury Maximov

Higher variability in grid conditions, resulting from growing renewable penetration and increased incidence of extreme weather events, has increased the difficulty of screening for scenarios that may lead to catastrophic cascading failures. Traditional power-flow-based tools for assessing cascading blackout risk are too slow to properly explore the space of possible failures and load/generation patterns. We add to the growing literature of faster graph-neural-network (GNN)-based techniques, developing two novel techniques for the estimation of blackout magnitude from initial grid conditions. First we propose several methods for employing an initial classification step to filter out safe ‘non-blackout’ scenarios prior to magnitude estimation. Second, using insights from the statistical properties of cascading blackouts, we propose a method for facilitating non-local message-passing in our GNN models. We validate these two approaches on a large simulated dataset, and show the potential of both to increase blackout size estimation performance. •Graph neural networks can estimate cascading blackout size from initial grid state.•The fast inference of machine-learning models can enable rapid scenario screening.•Statistical augmentation of graph input topology can increase estimation accuracy.•A pre-regression classification step can also increase estimation accuracy.

The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting. Both models achieved high ROC AUC scores: 0.948 for one month ahead and 0.617 for twelve months ahead forecasts, becoming closer to perfect ROC-AUC by 54% and 16%, respectively, c.t. classic approaches. •We improved quality for long-term, up to 12 months drought forecasting.•We adopted modern transformers and Convolutional LSTM to solve this problem.•We created an extensive test bed to evaluate models consisting of 5 diverse regions.•We reduced the gap to perfect ROC-AUC by 54% and 16%, respectively.

Agriculture, a cornerstone of human civilization, faces rising challenges from climate change, resource limitations, and stagnating yields. Precise crop production forecasts are crucial for shaping trade policies, development strategies, and humanitarian initiatives. This study introduces a comprehensive machine learning framework designed to predict crop production. We leverage CMIP5 climate projections under a moderate carbon emission scenario to evaluate the future suitability of agricultural lands and incorporate climatic data, historical agricultural trends, and fertilizer usage to project yield changes. Our integrated approach forecasts significant regional variations in crop production across Southeast Asia by 2028, identifying potential cropland utilization. Specifically, the cropland area in Indonesia, Malaysia, Philippines, and Viet Nam is projected to decline by more than 10% if no action is taken, and there is potential to mitigate that loss. Moreover, rice production is projected to decline by 19% in Viet Nam and 7% in Thailand, while the Philippines may see a 5% increase compared to 2021 levels. Our findings underscore the critical impacts of climate change and human activities on agricultural productivity, offering essential insights for policy-making and fostering international cooperation.

Despite significant economic and ecological effects, a higher level of renewable energy generation leads to increased uncertainty and variability in power injections, thus compromising grid reliability. To improve power grid security, we investigate a joint chance-constrained (CC) dc approximation of the ac optimal power flow (OPF) problem. The problem aims to find economically optimal power generation while guaranteeing that all power generation, line flows, and voltages remain within their bounds at the same time with a predefined probability. Unfortunately, the CC-dc-OPF problem is computationally intractable even if the distribution of renewables' fluctuations is specified. Moreover, existing approximate solutions to the joint CC OPF problem are overly conservative and computationally demanding and, therefore, have less value for the operational practice. This article proposes an importance sampling approach for constructing an efficient and reliable scenario approximation for CC-dc-OPF with theoretical guarantees on the number of samples required, which yields better sample complexity and accuracy than current state-of-the-art methods. The algorithm efficiently reduces the number of scenarios by generating and using only a few most important, thus enabling real-time solutions for test cases with up to several hundred buses.

Renewable energy sources (RES) are increasingly integrated into power systems to support the United Nations' Sustainable Development Goals of decarbonization and energy security. However, their low inertia and high uncertainty pose challenges to grid stability and increase the risk of blackouts. Stochastic chance-constrained optimization, particularly data-driven methods, offers solutions but can be time-consuming, especially when handling multiple system snapshots. This letter addresses a dynamic joint chance-constrained Direct Current Optimal Power Flow (DC-OPF) problem with Automated Generation Control (AGC) to facilitate cost-effective power generation while ensuring that balance and security constraints are met. We propose an approach for a data-driven approximation that includes a priori sample reduction, maintaining solution reliability while reducing the size of the data-driven approximation. Both theoretical analysis and empirical results demonstrate the superiority of this approach in handling generation uncertainty, requiring up to twice less data while preserving solution reliability.

This study addresses the critical global issue of food security, particularly under the influence of climate change on agricultural land suitability. The primary objective of our research is to predict the risks associated with land suitability degradation and changes in irrigation patterns, directly impacting food security. This research aligns with the United Nations' sustainable development goals to reduce hunger and malnutrition. Central Eurasia, a region facing unique economic and social challenges, serves as the focal point of our investigation, providing a pertinent example for analyzing the effects of climate change on food security. In our approach, we employ interpretable machine learning techniques to analyze the impact of climate change on agricultural land suitability under different carbon emission scenarios. The developed model demonstrates strong performance, evidenced by an accuracy of 86% and a mean average precision of 72% in a multi-class land suitability classification task. Focusing on the most vulnerable regions in Eastern Europe and Northern Asia, our research provides crucial insights for policymakers. These insights are instrumental for strategic planning, including the allocation of critical resources like water and fertilizers, to prevent humanitarian crises. The results demonstrate that machine learning can be a powerful tool in predicting and managing the impacts of climate change on food security.

At present, electricity generation is responsible for more than a quarter of the greenhouse gas emissions in the US. Integrating significant amounts of renewable energy sources into a power grid is probably the most accessible way to reduce carbon emissions from power grids and slow down climate change. Unfortunately, the most accessible renewable power sources, such as wind and solar, are highly intermittent and thus bring a lot of uncertainty to power grid operation and challenge existing optimization and control policies. The chance-constrained (CC) alternating current optimal power flow (AC-OPF) framework finds the minimum cost of generation dispatch, maintaining the power grid operation within security limits with a prescribed probability. Unfortunately, the AC-OPF problem's chance-constrained extension is non-convex, computationally challenging, and requires knowledge of system parameters and also needs additional assumptions to be made about the behavior of renewable generation probability distribution. Known linear and convex approximations to the above problems, though tractable, are too conservative for operational practice and do not consider uncertainty in system parameters. This paper presents an alternative data-driven approach for solving the stochastic AC-OPF problem, based on Gaussian process regression (GPR) to close this gap. The Gaussian process (GP) approach learns a simple yet non-convex data-driven approximation to the AC power flow equations that can incorporate uncertain inputs. The latter is then used to determine the solution of CC-OPF efficiently, by accounting for both input and parameter uncertainty. The practical efficiency of the proposed approach using different approximations for GP-uncertainty propagation is validated and illustrated using a number of standard IEEE test cases.

The alternating current (AC) chance-constrained optimal power flow (CC-OPF) problem addresses the economic efficiency of electricity generation and delivery under generation uncertainty. The latter is intrinsic to modern power grids because of the high amount of renewables. Despite its academic success, the AC CC-OPF problem is highly nonlinear and computationally demanding, which limits its practical impact. For improving the AC-OPF problem complexity/accuracy trade-off, the paper proposes a fast data-driven setup that uses the sparse and hybrid Gaussian processes (GP) framework to model the power flow equations with input uncertainty. We advocate the efficiency of the proposed approach by a numerical study over multiple IEEE test cases that show up to two times speed-up and more accurate solutions over state-of-the-art methods.

The Gaussian Process (GP) based Chance-Constrained Optimal Power Flow (CC-OPF) is an open-source Python code developed for solving economic dispatch (ED) problem in modern power grids. In recent years, integrating a significant amount of renewables into a power grid causes high fluctuations and thus brings a lot of uncertainty to power grid operations. This fact makes the conventional model-based CC-OPF problem non-convex and computationally complex to solve. The developed tool presents a novel data-driven approach based on the GP regression model for solving the CC-OPF problem with a trade-off between complexity and accuracy. The proposed approach and developed software can help system operators to effectively perform ED optimization in the presence of large uncertainties in the power grid. •GP CC-OPF hybrid approach for chance-constrained OPF is proposed.•A sparse Gaussian process model is considered for the trade-off between accuracy and complexity.•The proposed approach does not require information about the topology and parameters of the electrical grid.•GP CC-OPF can help the power system operator to plan generation dispatch under injection uncertainties.

Hail risk assessment is crucial for businesses, particularly in the agricultural and insurance sectors, as it helps estimate and mitigate potential losses. Although significant attention has been given to short-term hail forecasting, the lack of research on climatological-scale hail risk estimation adds to the overall complexity of this task. Hail events are rare and localized, making their prediction a long-term open challenge. One approach to address this challenge is to develop a model that classifies vertical profiles of meteorological variables as favorable for hail formation while neglecting important spatial and temporal information. The main advantages of this approach lie in its computational efficiency and scalability. A more advanced strategy involves combining convolutional layers and recurrent neural network blocks to process geospatial and temporal data, respectively. This study compares the effectiveness of these two approaches and introduces a model suitable for forecasting changes in hail frequency.