Workshop: Tackling Climate Change with ML

David Dao, Evan Sherwin, Priya Donti, Lauren Kuntz, Lynn Kaack, Yumna Yusuf, David Rolnick, Catherine Nakalembe, Claire Monteleoni, Yoshua Bengio

2020-12-11T03:00:00-08:00 - 2020-12-11T16:00:00-08:00
Abstract: Climate change is one of the greatest problems society has ever faced, with increasingly severe consequences for humanity as natural disasters multiply, sea levels rise, and ecosystems falter. Since climate change is a complex issue, action takes many forms, from designing smart electric grids to tracking greenhouse gas emissions through satellite imagery. While no silver bullet, machine learning can be an invaluable tool in fighting climate change via a wide array of applications and techniques. These applications require algorithmic innovations in machine learning and close collaboration with diverse fields and practitioners. This workshop is intended as a forum for those in the machine learning community who wish to help tackle climate change. Building on our past workshops on this topic, this workshop aims to especially emphasize the pipeline to impact, through conversations about machine learning with decision-makers and other global leaders in implementing climate change strategies. The all-virtual format of NeurIPS 2020 provides a special opportunity to foster cross-pollination between researchers in machine learning and experts in complementary fields.



Chat is not available.


2020-12-11T03:00:00-08:00 - 2020-12-11T03:35:00-08:00
Welcome and opening remarks
2020-12-11T03:35:00-08:00 - 2020-12-11T04:00:00-08:00
Keynote by Rose Mwebaza
2020-12-11T04:00:00-08:00 - 2020-12-11T04:05:00-08:00
Introduction to Spotlights
2020-12-11T04:05:00-08:00 - 2020-12-11T04:15:00-08:00
Spotlight: Deep Learning for Climate Model Output Statistics
Michael Steininger
Climate models are an important tool for the assessment of prospective climate change effects but they suffer from systematic and representation errors, especially for precipitation. Model output statistics (MOS) reduce these errors by fitting the model output to observational data with machine learning. In this work, we explore the feasibility and potential of deep learning with convolutional neural networks (CNNs) for MOS. We propose the CNN architecture ConvMOS specifically designed for reducing errors in climate model outputs and apply it to the climate model REMO. Our results show a considerable reduction of errors and mostly improved performance compared to three commonly used MOS approaches.
2020-12-11T04:15:00-08:00 - 2020-12-11T04:22:00-08:00
Spotlight: An Enriched Automated PV Registry: Combining Image Recognition and 3D Building Data
Kevin Mayer
While photovoltaic (PV) systems are installed at an unprecedented rate, reliable information on an installation level remains scarce. As a result, automatically created PV registries are a timely contribution to optimize grid planning and operations. This paper demonstrates how aerial imagery and three-dimensional building data can be combined to create an address-level PV registry, specifying area, tilt, and orientation angles. We demonstrate the benefits of this approach for PV capacity estimation. In addition, this work presents, for the first time, a comparison between automated and officially-created PV registries. Our results indicate that our enriched automated registry proves to be useful to validate, update, and complement official registries.
2020-12-11T04:22:00-08:00 - 2020-12-11T04:32:00-08:00
Spotlight: Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery
Thomas Chen
Natural disasters ravage the world's cities, valleys, and shores on a monthly basis. Having precise and efficient mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, we train multiple convolutional neural networks to assess building damage on a per-building basis. In order to investigate how to best classify building damage, we present a highly interpretable deep-learning methodology that seeks to explicitly convey the most useful information required to train an accurate classification model. We also delve into which loss functions best optimize these models. Our findings include that ordinal-cross entropy loss is the most optimal loss function to use and that including the type of disaster that caused the damage in combination with a pre- and post-disaster image best predicts the level of damage caused. Our research seeks to computationally contribute to aiding in this ongoing and growing humanitarian crisis, heightened by climate change.
2020-12-11T04:32:00-08:00 - 2020-12-11T04:42:00-08:00
Spotlight: A Machine Learning Approach to Methane Emissions Mitigation in the Oil and Gas Industry
Jiayang Wang
Reducing methane emissions from the oil and gas sector is a key component of climate policy in the United States. Methane leaks across the supply chain are stochastic and intermittent, with a small number of sites (‘super-emitters’) responsible for a majority of emissions. Thus, cost-effective emissions reduction critically relies on effectively identifying the super-emitters from thousands of well-sites and millions of miles of pipelines. Conventional approaches such as walking surveys using optical gas imaging technology are slow and time-consuming. In addition, several variables contribute to the formation of leaks such as infrastructure age, production, weather conditions, and maintenance practices. Here, we develop a machine learning algorithm to predict high-emitting sites that can be prioritized for follow-up repair. Such prioritization can significantly reduce the cost of surveys and increase emissions reductions compared to conventional approaches. Our results show that the algorithm using logistic regression performs the best out of several algorithms. The model achieved a 70% accuracy rate with a 57% recall and a 66% balanced accuracy rate. Compared to the conventional approach, the machine learning model reduced the time to achieve a 50% emissions mitigation target by 42%. Correspondingly, the mitigation cost reduced from $85/t CO2e to $49/t CO2e.
2020-12-11T04:42:00-08:00 - 2020-12-11T04:52:00-08:00
Spotlight: RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale
Catherine Tong
Climate change is expected to aggravate extreme precipitation events, directly impacting the livelihood of millions. Without a global precipitation forecasting system in place, many regions -- especially those constrained in resources to collect expensive groundstation data -- are left behind. To mitigate such unequal reach of climate change, a solution is to alleviate the reliance on numerical models (and by extension groundstation data) by enabling machine-learning-based global forecasts from satellite imagery. Though prior works exist in regional precipitation nowcasting, there lacks work in global, medium-term precipitation forecasting. Importantly, a common, accessible baseline for meaningful comparison is absent. In this work, we present RainBench, a multi-modal benchmark dataset dedicated to advancing global precipitation forecasting. We establish baseline tasks and release PyRain, a data-handling pipeline to enable efficient processing of decades-worth of data by any modeling framework. Whilst our work serves as a basis for a new chapter on global precipitation forecast from satellite imagery, the greater promise lies in the community joining forces to use our released datasets and tools in developing machine learning approaches to tackle this important challenge.
2020-12-11T04:52:00-08:00 - 2020-12-11T05:00:00-08:00
Introduction to first poster session
2020-12-11T05:00:00-08:00 - 2020-12-11T06:00:00-08:00
Poster session 1
2020-12-11T06:00:00-08:00 - 2020-12-11T06:09:00-08:00
Introduction to Spotlights
2020-12-11T06:09:00-08:00 - 2020-12-11T06:19:00-08:00
Spotlight: The Peruvian Amazon Forestry Dataset: A Leaf Image Classification Corpus
Gerson Vizcarra Aguilar
This paper introduces the Peruvian Amazon Forestry Dataset, which includes 59,441 leaves samples from ten of the most profitable and endangered Amazon timber-tree species. Besides, the proposal includes a background removal algorithm to feed a fine-tuned CNN. We evaluate the quantitative (accuracy metric) and qualitative (visual interpretation) impacts of each stage by ablation experiments. The results show a 96.64 % training accuracy and 96.52 % testing accuracy on the VGG-19 model. Furthermore, the visual interpretation of the model evidences that leaf venations have the highest correlation in the plant recognition task.
2020-12-11T06:19:00-08:00 - 2020-12-11T06:25:00-08:00
Spotlight: Data-driven modeling of cooling demand in a commercial building
Aqsa Naeem
Heating, ventilation, and air conditioning (HVAC) systems account for 30% of the total energy consumption in buildings. Design and implementation of energy-efficient schemes can play a pivotal role in minimizing energy usage. As an important first step towards improved HVAC system controls, this study proposes a new framework for modeling the thermal response of buildings by leveraging data measurements and formulating a data-driven system identification model. The proposed method combines principal component analysis (PCA) to identify the most significant predictors that influence the cooling demand of a building with an auto-regressive integrated moving average with exogenous variables (ARIMAX) model. The performance of the developed model was evaluated both analytically and visually. It was found that our PCA-based ARIMAX (2-0-5) model was able to accurately forecast the cooling demand for the prediction horizon of 7 days. In this work, the actual measurements from a university campus building are used for model development and validation.
2020-12-11T06:25:00-08:00 - 2020-12-11T06:37:00-08:00
Spotlight: Structural Forecasting for Tropical Cyclone Intensity Prediction: Providing Insight with Deep Learning
Trey H McNeely
Tropical cyclone (TC) intensity forecasts are ultimately issued by human forecasters. The human in-the-loop pipeline requires that any forecasting guidance must be easily digestible by TC experts if it is to be adopted at operational centers like the National Hurricane Center. Our proposed framework leverages deep learning to provide forecasters with something neither end-to-end prediction models nor traditional intensity guidance does: a powerful tool for monitoring high-dimensional time series of key physically relevant predictors and the means to understand how the predictors relate to one another and to short-term intensity changes.
2020-12-11T06:37:00-08:00 - 2020-12-11T06:47:00-08:00
Spotlight: FireSRnet: Geoscience-driven super-resolution of future fire risk from climate change
Tristan Ballard
With fires becoming increasingly frequent and severe across the globe in recent years, understanding climate change’s role in fire behavior is critical for quantifying current and future fire risk. However, global climate models typically simulate fire behavior at spatial scales too coarse for local risk assessments. Therefore, we propose a novel approach towards super-resolution (SR) enhancement of fire risk exposure maps that incorporates not only 2000 to 2020 monthly satellite observations of active fires but also local information on land cover and temperature. Inspired by SR architectures, we propose an efficient deep learning model trained for SR on fire risk exposure maps. We evaluate this model on resolution enhancement and find it outperforms standard image interpolation techniques at both 4x and 8x enhancement while having comparable performance at 2x enhancement. We then demonstrate the generalizability of this SR model over northern California and New South Wales, Australia. We conclude with a discussion and application of our proposed model to climate model simulations of fire risk in 2040 and 2100, illustrating the potential for SR enhancement of fire risk maps from the latest state-of-the-art climate models.
2020-12-11T06:47:00-08:00 - 2020-12-11T06:57:00-08:00
Spotlight: Spatiotemporal Features Improve Fine-Grained Butterfly Image Classification
Marta Skreta
Understanding the changing distributions of butterflies gives insight into the impacts of climate change across ecosystems and is a prerequisite for conservation efforts. eButterfly is a citizen science website created to allow people to track the butterfly species around them and use these observations to contribute to research. However, correctly identifying butterfly species is a challenging task for non-specialists and currently requires the involvement of entomologists to verify the labels of novice users on the website. We have developed a computer vision model to label butterfly images from eButterfly automatically, decreasing the need for human experts. We employ a model that incorporates geographic and temporal information of where and when the image was taken, in addition to the image itself. We show that we can successfully apply this spatiotemporal model for fine-grained image recognition, significantly improving the accuracy of our classification model compared to a baseline image recognition system trained on the same dataset.
2020-12-11T07:00:00-08:00 - 2020-12-11T08:00:00-08:00
Climate Change and ML for Policy
Angel Hsu, Dava Newman, James Rattling Leaf, Sr., Mouhamadou M Cisse
2020-12-11T08:00:00-08:00 - 2020-12-11T09:00:00-08:00
Poster session 2
2020-12-11T09:00:00-08:00 - 2020-12-11T09:10:00-08:00
Introduction to Zico Kolter
2020-12-11T09:10:00-08:00 - 2020-12-11T09:40:00-08:00
Keynote by Zico Kolter
J. Zico Kolter
2020-12-11T09:40:00-08:00 - 2020-12-11T10:00:00-08:00
Q&A with Zico Kolter
2020-12-11T10:00:00-08:00 - 2020-12-11T11:00:00-08:00
Climate Change and ML in the Private Sector
Aisha Walcott-Bryant, Lea Boche, Anima Anandkumar
2020-12-11T11:00:00-08:00 - 2020-12-11T11:05:00-08:00
Introduction to Spotlights
2020-12-11T11:05:00-08:00 - 2020-12-11T11:15:00-08:00
Spotlight: Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya
Kris Sankaran
Glacier mapping is key to ecological monitoring in the Hindu Kush Himalaya region. Climate change poses a risk to individuals whose livelihoods depend on the health of glacier ecosystems. In this work, we present a machine learning based approach to support ecological monitoring, with a focus on glaciers. Our approach is based on semi-automated mapping from satellite images. We utilize readily available remote sensing data to create a model to identify and outline both clean ice and debris-covered glaciers from satellite imagery. We also release data and develop a web tool that allows experts to visualize and correct model predictions, with the ultimate aim of accelerating the glacier mapping process.
2020-12-11T11:15:00-08:00 - 2020-12-11T11:25:00-08:00
Spotlight: Wildfire Smoke and Air Quality: How Machine Learning Can Guide Forest Management
Lorenzo Tomaselli
Prescribed burns are currently the most effective method of reducing the risk of widespread wildfires, but a largely missing component in forest management is knowing which fuels one can safely burn to minimize exposure to toxic smoke. Here we show how machine learning, such as spectral clustering and manifold learning, can provide interpretable representations and powerful tools for differentiating between smoke types, hence providing forest managers with vital information on effective strategies to reduce climate-induced wildfires while minimizing production of harmful smoke.
2020-12-11T11:25:00-08:00 - 2020-12-11T11:36:00-08:00
Spotlight: OGNet: Towards a Global Oil and Gas Infrastructure Database using Deep Learning on Remotely Sensed Imagery
Hao Sheng
At least a quarter of the warming that the Earth is experiencing today is due to anthropogenic methane emissions. There are multiple satellites in orbit and planned for launch in the next few years which can detect and quantify these emissions; however, to attribute methane emissions to their sources on the ground, a comprehensive database of the locations and characteristics of emission sources worldwide is essential. In this work, we develop deep learning algorithms that leverage freely available high-resolution aerial imagery to automatically detect oil and gas infrastructure, one of the largest contributors to global methane emissions. We use the best algorithm, which we call OGNet, together with expert review to identify the locations of oil refineries and petroleum terminals in the U.S. We show that OGNet detects many facilities which are not present in four standard public datasets of oil and gas infrastructure. All detected facilities are associated with characteristics critical to quantifying and attributing methane emissions, including the types of infrastructure and number of storage tanks. The data curated and produced in this study is freely available at https://link/provided/in/camera/ready/version.
2020-12-11T11:36:00-08:00 - 2020-12-11T11:45:00-08:00
Spotlight: Climate Change Driven Crop Yield Failures
Somya Sharma
The effect of extreme temperatures, precipitation and variations in other meteorological factors affect crop yields, and hence climate change jeopardizes the entire food supply chain and dependent economic activities. We utilize Deep Neural Networks and Gaussian Processes for understanding crop yields as functions of climatological variables, and use change detection techniques to identify climatological thresholds where yield drops significantly.
2020-12-11T11:45:00-08:00 - 2020-12-11T11:55:00-08:00
Spotlight: Towards Tracking the Emissions of Every Power Plant on the Planet
Heather Couture
Greenhouse gases emitted from fossil-fuel-burning power plants are a major contributor to climate change. Current methods to track emissions from individual sources are expensive and only used in a few countries. While carbon dioxide concentrations can be measured globally using remote sensing, direct methods do not provide sufficient spatial resolution to distinguish emissions from different sources. We use machine learning to infer power generation and emissions from visible and thermal power plant signatures in satellite images. By training on a data set of power plants for which we know the generation or emissions, we are able to apply our models globally. This paper demonstrates initial progress on this project by predicting whether a power plant is on or off from a single satellite image.
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Poster session 3
2020-12-11T13:00:00-08:00 - 2020-12-11T13:10:00-08:00
Introduction to Jennifer Chayes
2020-12-11T13:10:00-08:00 - 2020-12-11T13:40:00-08:00
Keynote by Jennifer Chayes
Jennifer Chayes
2020-12-11T13:40:00-08:00 - 2020-12-11T14:00:00-08:00
Q&A with Jennifer Chayes
2020-12-11T14:00:00-08:00 - 2020-12-11T14:50:00-08:00
Fireside Chat with Vinod Khosla
Vinod Khosla
2020-12-11T14:50:00-08:00 - 2020-12-11T15:15:00-08:00
Closing remarks
2020-12-11T15:15:00-08:00 - 2020-12-11T16:00:00-08:00
Poster reception
DeepWaste: Applying Deep Learning to Waste Classification for a Sustainable Planet
Yash Narayan
Monitoring the Impact of Wildfires on Tree Species with Deep Learning
Short-Term Solar Irradiance Forecasting Using Calibrated Probabilistic Models
Eric Zelikman
Artificial Intelligence, Machine Learning and Modeling for Understanding the Oceans and Climate Change
Luis Martí
Deep learning architectures for inference of AC-OPF solutions
Thomas Falconer
Short-term prediction of photovoltaic power generation using Gaussian process regression
Yahya Al Lawati
Movement Tracks for the Automatic Detection of Fish Behavior in Videos
Declan GD McIntosh
Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery
Issam Hadj Laradji
EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts
Christian Requena-Mesa
Characterization of Industrial Smoke Plumes from Remote Sensing Data
Michael Mommert
Quantifying the presence of air pollutants over a road network in high spatio-temporal resolution
Matteo Bohm
Optimal District Heating in China with Deep Reinforcement Learning
Adrien Le Coz
Can Federated Learning Save The Planet ?
Xinchi Qiu
A Comparison of Data-Driven Models for Predicting Stream Water Temperature
Helen Weierbach
Machine Learning towards a Global Parametrization of Atmospheric New Particle Formation and Growth
Mihalis Nicolaou
Analyzing Sustainability Reports Using Natural Language Processing
Sasha Luccioni
High-resolution global irrigation prediction with Sentinel-2 30m data
Will Hawkins
pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Research
Gonzague Henri
A Temporally Consistent Image-based Sun Tracking Algorithm for Solar Energy Forecasting Applications
Quentin Paletta
Investigating two super-resolution methods for downscaling precipitation: ESRGAN and CAR
Campbell Watson
Explaining Complex Energy Systems: A Challenge
Jonas Hülsmann
HECT: High-Dimensional Ensemble Consistency Testing for Climate Models
Nic Dalmasso
ACED: Accelerated Computational Electrochemical systems Discovery
Rachel C Kurchin
Machine learning for advanced solar cell production: adversarial denoising, sub-pixel alignment and the digital twin
Matthias Demant
ClimaText: A Dataset for Climate Change Topic Detection
Markus Leippold
Estimating Forest Ground Vegetation Cover From Nadir Photographs Using Deep Convolutional Neural Networks
Martin Barczyk
Graph Neural Networks for Improved El Niño Forecasting
Salva Rühling Cachay
Hyperspectral Remote Sensing of Aquatic Microbes to Support Water Resource Management
Grace Kim
Long-Range Seasonal Forecasting of 2m-Temperature with Machine Learning
Etienne Vos
Short-term PV output prediction using convolutional neural network: learning from an imbalanced sky images dataset via sampling and data augmentation
Yuhao Nie
Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks
Brian Hutchinson
Annual and in-season mapping of cropland at field scale with sparse labels
Gabriel Tseng
ForestNet: Classifying Drivers of Deforestation in Indonesia using Deep Learning on Satellite Imagery
Jeremy Irvin
Forecasting Marginal Emissions Factors in PJM
Amy Wang
Is Africa leapfrogging to renewables or heading for carbon lock-in? A machine-learning-based approach to predicting success of power-generation projects
Galina Alova
Monitoring Shorelines via High-Resolution Satellite Imagery and Deep Learning
Venkatesh Ramesh
Do Occupants in a Building exhibit patterns in Energy Consumption? Analyzing Clusters in Energy Social Games
Hari Prasanna Das
Privacy Preserving Demand Forecasting to Encourage Consumer Acceptance of Smart Energy Meters
Chris Briggs
Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery
Valentina Zantedeschi
Learning the distribution of extreme precipitation from atmospheric general circulation model variables
Philipp Hess
NightVision: Generating Nighttime Satellite Imagery from Infra-Red Observations
Paula Harder
A Way Toward Low-Carbon Shipping: Improving Port Operations Planning using Machine Learning
Sara El Mekkaoui
Electric Vehicle Range Improvement by Utilizing Deep Learning to Optimize Occupant Thermal Comfort
Alok Warey
Climate-FEVER: A Dataset for Verification of Real-World Climate Claims
Markus Leippold
Residue Density Segmentation for Monitoring and Optimizing Tillage Practices
Jennifer Hobbs
Towards DeepSentinel: An extensible corpus of labelled Sentinel-1 and -2 imagery and a proposed general purpose sensor-fusion semantic embedding model
Lucas Kruitwagen
Machine Learning Climate Model Dynamics: Offline versus Online Performance
Noah Brenowitz
Spatio-Temporal Learning for Feature Extraction inTime-Series Images
Gael Kamdem De Teyou
Understanding global fire regimes using Artificial Intelligence
Cristobal Pais
Mangrove Ecosystem Detection using Mixed-Resolution Imagery with a Hybrid-Convolutional Neural Network
Dillon Hicks
Deep Fire Topology: Understanding the role of landscape spatial patterns in wildfire susceptibility
Cristobal Pais
Street to Cloud: Improving Flood Maps With Crowdsourcing and Semantic Segmentation
Veda Sunkara
Leveraging Machine learning for Sustainable and Self-sufficient Energy Communities
Anthony Faustine
Storing Energy with Organic Molecules: Towards a Metric for Improving Molecular Performance for Redox Flow Batteries
Luis Martin Mejia Mendoza
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
Robbie Jones
A Multi-source, End-to-End Solution for Tracking Climate Change Adaptation in Agriculture
Alejandro Coca-Castro
Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery
Tomas Langer
Meta-modeling strategy for data-driven forecasting
Dominic Skinner
Predicting the Solar Potential of Rooftops using Image Segmentation and Structured Data
Daniel de Barros Soares
Accurate river level predictions using a Wavenet-like model
Shannon Doyle
Using attention to model long-term dependencies in occupancy behavior
Max Kleinebrahm
Satellite imagery analysis for Land Use, Land Use Change and Forestry: A pilot study in Kigali, Rwanda
Bright Aboh
Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse
Ancil Crayton
Quantitative Assessment of Drought Impacts Using XGBoost based on the Drought Impact Reporter
Beichen Zhang
Predicting Landsat Reflectance with Deep Generative Fusion
Shahine Bouabid
FlowDB: A new large scale river flow, flash flood, and precipitation dataset
Isaac Godfried
Machine Learning Informed Policy for Environmental Justice in Atlanta with Climate Justice Implications
Lelia Hampton
VConstruct: Filling Gaps in Chl-a Data Using a Variational Autoencoder
Matthew Ehrler
The Human Effect Requires Affect: Addressing Social-Psychological Factors of Climate Change with Machine Learning
Kyle Tilbury
Revealing the Oil Majors' Adaptive Capacity to the Energy Transition with Deep Multi-Agent Reinforcement Learning
Dylan Radovic
Expert-in-the-loop Systems Towards Safety-critical Machine Learning Technology in Wildfire Intelligence
Maria João Sousa
Automated Salmonid Counting in Sonar Data
Peter Kulits
A Generative Adversarial Gated Recurrent Network for Power Disaggregation & Consumption Awareness
Maria Kaselimi
OfficeLearn: An OpenAI Gym Environment for Building Level Energy Demand Response
Lucas Spangher
Physics-constrained Deep Recurrent Neural Models of Building Thermal Dynamics
Jan Drgona
Emerging Trends of Sustainability Reporting in the ICT Industry: Insights from Discriminative Topic Mining
Lin Shi
Context-Aware Urban Energy Efficiency Optimization Using Hybrid Physical Models
Ben Choi
Deep Reinforcement Learning in Electricity Generation Investment for the Minimization of Long-Term Carbon Emissions and Electricity Costs
Alex Kell
Automated Identification of Oil Field Features using CNNs