The role of deep learning in science is at a turning point, with weather, climate, and Earth systems modeling emerging as an exciting application area for physics-informed deep learning that can more effectively identify nonlinear relationships in large datasets, extract patterns, emulate complex physical processes, and build predictive models.

“Deep learning has had unprecedented success in some very challenging problems, but scientists want to understand exactly how these models work and why they do the things they do,” said Karthik Kashinath, a computer scientist and engineer in the Data & Analytics Services Group (DAS) at the National Energy Research Scientific Computing Center (NERSC) who has been deeply involved in NERSC’s research and education efforts in this area. “A key goal of deep learning for science is how do you design and train a neural network so that it can capture accurately the complexity of the processes it seeks to model, emulate, or predict, and we’re developing ways to infuse physics and domain knowledge into these neural networks so that they obey the laws of nature and their results are explainable, robust, and trustworthy.”

We caught up with Kashinath following the Artificial Intelligence for Earth System Science (AI4ESS) Summer School, a week-long virtual event hosted in June by the National Center for Atmospheric Research (NCAR) and the University Corporation for Atmospheric Research (UCAR) that was attended by more than 2,400 researchers from around the world. Kashinath was involved in organizing and presenting at the event, along with David John Gagne and Rich Loft of NCAR. Much of Kashinath’s current research focuses on the application of deep learning methods to climate and Earth systems modeling.

How are deep learning methodologies being adopted in weather, climate, and Earth systems research?

In recent years we’ve seen a significant rise in the use of deep learning in science, not just in augmenting, enhancing or replacing existing methods, but also for discovering new science in physics, chemistry, biology, medicine, and more – discoveries that were nearly impossible with traditional statistical methods. We are now starting to see the same in the Earth sciences, with the number of publications in journals like Geophysical Research Letters and Nature Geoscience rising and scientific conferences now featuring entire tracks involving machine and deep learning.

What does deep learning bring to the table?

It is extremely powerful in pattern recognition and discovering very complex nonlinear relationships that exist in large datasets, both of which are critical for developing models of Earth science systems. The key goal of a weather or climate modeler is to understand the ways in which processes in nature operate and to model them in an effective manner so we can predict the future of climate change and extreme weather events. Deep learning offers new methods for using existing data to understand how these processes operate and to develop models for them that are not only accurate and effective but also computationally much faster than traditional methods. Traditionally, climate and weather models solve large systems of coupled nonlinear partial differential equations, which is extremely computationally intensive. Deep learning is starting to augment, enhance, or even replace parts of these models with very efficient and fast physical process emulators. And that’s a significant step forward.

Pattern recognition is another area where deep learning is influencing Earth systems research. The DAS group at NERSC has been pushing hard on pattern recognition for detecting and tracking weather and climate patterns in large datasets. The 2018 Gordon Bell prize for exascale climate analytics using deep learning testifies to our contributions in that area. Given that we already have petabytes of climate data and that it is increasing at a crazy rate, it is physically impossible to sift through and recognize the key features and patterns using traditional statistical approaches. Deep learning offers very fast ways to mine that data and extract useful information such as extreme weather patterns.

A third area is downscaling; that is, given a low-resolution dataset, how do you produce very high-resolution data that is necessary for things like planning, especially on regional and local scales? Part of the grand challenge of climate science is how to build very high-resolution models that are accurate and produce data that we can reliably work with. One way to attack the problem is to say okay, we know these models are extremely expensive, and in the foreseeable future – even with computing getter faster and better – we’re really not going to be able to build reliable global climate models at a spatial resolution of 1 km or finer. So if we can create a deep learning model that takes low-resolution climate data and produces high-resolution data that is physically meaningful, reliable, and accurate – that is a game changer.

What is a grand challenge for deep learning applied to Earth system science?

I come from a background in fluid dynamics, where modeling turbulence is a long-standing grand challenge. A similar challenge in the atmospheric sciences is modeling clouds. All climate models have parameterizations – components in the climate model that describe how various physical processes behave and interact with each other. In the atmosphere that includes how clouds form, how radiation works, when and where precipitation happens, etc. Cloud modeling is also known to be the largest source of uncertainty in climate model projections, and for decades one of the big challenges has been how to reduce the uncertainty. Models have become much more complex and capture many more physical phenomena, but they still have large uncertainties in their predictions. So one area where deep learning could have a significant impact is to help us build better emulators of atmospheric processes like clouds, with the goal of reducing the uncertainties in predictions. That is a very concrete scientific goal.

As you look ahead, what are you most excited about in terms of the impact of deep learning on climate and Earth systems research?

The major pushback we’ve had from the scientific community is that neural networks are black boxes that are hard to understand and interpret, and scientists obviously would like to understand exactly how these neural networks work and why they do the things they do. So one thing I’m really excited about is developing better ways to interpret and understand these networks and incorporate the knowledge that we have about the physics of the Earth system into these models so they are more robust, reliable, trustworthy, interpretable, explainable, and transparent. The goal is to convince ourselves that these models are behaving in ways that respect the physics of nature, are effectively using the domain knowledge that we have, and are making predictions that we can trust. I was invited to submit a paper to Proceedings of the Royal Society on exactly this topic, “Physics-informed Deep Learning for Weather and Climate Modeling,” which is now under review.

I’m also excited about proving, in operation, that these deep learning models provide the computational speedup we claim they will provide when we embed them into a large climate or weather model. For example, the European Weather Forecasting Center has started to replace some parts of its weather forecasting model with machine and deep learning models, and they are already starting to see benefits. In the U.S., NCAR and the National Oceanic and Atmospheric Administration are also starting to replace parts of their climate and weather models with machine learning and deep learning models, and a number of academic and industry-based research groups are working on related projects. Chris Bretherton, one of the world’s leading climate scientists, heads a group at the University of Washington that is working to replace some of the complicated cloud processes in these large climate models with deep learning methods. So I’m looking forward to seeing their results in a year or two on speedup and performance.

What was the focus of the AI4ESS event, and why was it so well-attended?

The Artificial Intelligence for Earth System Science (AI4ESS) Summer School focused on how attendees can strengthen their background in statistics and machine learning, learn the fundamentals of deep learning and neural networks, and learn how to use these for challenging problems in the Earth system sciences. We had an overwhelming response to the school – it was supposed to be an in-person event in Boulder, Colo., with a capacity of 80 students. But once it went virtual, we had 2,400 attendees from 40 countries across the globe. It was live-streamed through UCAR and they tracked the daily log-ins.

There was great participation throughout the week. We had invited speakers every day – three lectures a day, so 15 lectures over the week – with experts from machine learning, deep learning, and the Earth sciences. Each day there was also a panel discussion for 30 minutes over lunch, and for me, these were super exciting because all of these experts were discussing and debating about the challenges and opportunities of using machine learning and deep learning for Earth system science. The school also held a week-long hackathon, where teams of six each chose a project from six different problems to work on for the week. About 500 people participated in the hackathon, with a lot of collaboration and interaction, including individual Slack channels for each of the hackathon teams. There were also Slack channels for the entire week of the summer school on various things: lecture-related Q&As, hackathon challenge problems, technical tips and tricks in machine learning and deep learning, etc. So there was a lot of Slack activity going on, with people exchanging ideas, sharing results, and so forth.

Why is everyone so keen on learning this stuff?

I think the community, especially the younger scientists, see that deep learning can be a game changer in science and they don’t want to be left behind. They believe that it is going to be mainstream soon and that it is going to be essential for doing science. That’s the main motivator. So AI4ESS focused on teaching the fundamentals and laying the groundwork for them to begin applying machine and deep learning successfully to their research.

The post Q&A: Physical scientists turn to deep learning to improve Earth systems modeling appeared first on Artificial Intelligence.

Companies operating in the Consumer Packaged Goods (CPG) segment work under a unique ecosystem. They have to strike a balance between maintaining top-line revenue growth and managing sustainable profit margins. The reason why the task becomes difficult is because they have to do so while managing a dynamic set of operations. Moreover, a shift in consumer preferences, advances in data & analytics, channel shifts, and pandemic-led disruptions have created new challenges for retail and CPG companies.

However, in the current market scenario, they also have the opportunity to upgrade RGM, thereby creating equilibrium between growth and efficiency. They can increase the use of complex and action-oriented analytics across the product catalogue, optimize value capture approaches, use automated technology, and partner with retailers for shared value creation.

Why upgrading RGM is important for CPG companies?

Competitiveness has considerably intensified within the CPG industry. Today, there are limited avenues in terms of customer touchpoints vis-a-vis the year-ago period. The demand pockets have also changed dramatically and so has the New Normal’s supply chain management. CPG businesses today need to unlock as much efficiency from as many avenues as possible.

For those who cannot determine whether they should upgrade their RGM or not, there are a few questions that will help them overcome this quandary. Is your inflation getting outpaced by net revenue realization? Are your capabilities increasing faster than your competitors and retailers? Is the RGM beyond silo and addresses online business as well? Has it been integrated to your overall business strategy and at scale? Are you sufficiently leveraging data and analytics to grow revenue?

If the answer to a majority of these questions is ‘Yes’, then you don’t need to upgrade your RGM. If it is ‘No’, then it is time to think otherwise. Depending on the answers, companies must commit one or more paths towards RGM differentiation today to help their business triumph in the market. Leading data analytics solution providers help you to lay out and execute RGM roadmap for both strategic RGM and tactical implementations seamlessly.

Role of artificial intelligence in revenue growth

Over the last decade, a lot of CPG companies have implemented & tried to bring in new data and technologies for revenue growth management. This has enabled them to gain knowledge on what, how, and why shoppers buy and consume. Organisations are further bringing in MACRO data and other studies like segmentation into the toolkit. While RGM is important to operate effectively in the market, companies no longer have a competitive edge.

For sustainable revenues and growth, CPG companies must adopt AI. Its importance in terms of advanced capabilities in pricing, promotions, assortments, and trade investment will only increase as the competition intensifies within the CPG industry.

Artificial intelligence and ML provide companies with the scalable capability to utilize the power of data and navigate complexity. AI lets CPGs and retailers access customer insights and predict future actions based on the past behaviours. AI uses predictive analysis to help understand the desires, motivations, and actions across physical and digital channels. It allows retailers and suppliers to improve functions such as executing hyper-personalized campaigns and trade promotions efforts.

Artificial intelligence brings in key aspects such as

• The ability to add in a variety of data sources.
• Quick feedback loop. It creates a learning mechanism to update the model/recommendations on the basis of the ever-changing market dynamics (such as consumer preferences)
• Speed to market. For instance, one of the modules within RGM can help identify & recommend price tiers, better trade investments, and so forth. It can also predict future out-of-stock incidences more accurately, thereby helping to optimize supply chains.

Such solutions provide swift and actionable insights that lead to better conversion/engagement rates with customers. It further leverages predictive algorithms for guided decision making, scenario planning, and simulation to drive prepared outcomes.

How artificial intelligence supports RGM:

The most critical function of AI in RGM is that it converts plain data into the famous ‘So What’ or the relevant implication/suggestion. It helps in shifting the output from ‘Insights’ to Recommendations.

These are some of its other advantages:

• Unified Data View: AI helps leaders understand the consumer and drive efficacy with a unified data view. It reveals how actions impact Key Performance Indicators (KPIs) across the business, and not only within each function. The algorithmic recommendations enable one to look beyond interim improvements and suggest actions that achieve end-goals.

AI unifies data scattered across multiple channels and sources (both structured and unstructured). It can detect and classify relevant information on consumers relating to individual household information, scan cart-level data at point-of-sale, social sentiment, purchase behaviour across channels, travel patterns and dwell time in various venues to gain deep insights of the consumer path to purchase. AI technology enables teams to comb through massive data, analyse, and decode customer shopping behaviour on micro parameters. This also helps CPG companies create a 360-degree customer view.

• Granular Predictive Models: Predictive AI models built on unified data are very granular and micro-segmented models. This makes them capable of large-scale analysis with tailored objectives and limitations at all levels. They can learn from history and can also predict probable future outcomes. Such models can also estimate baseline and raise forecasts combining a diverse set of influencing factors. They leverage deep learning to recognize shopping patterns and complex interactions. For instance, switching between brands within a category, or switching between channels, or even between shopping occasions. They can identify interrelated patternsbetween trade and other actions in the market.

AI provides minutest insights to understand each customer by sifting through massive structured and unstructured datasets from the first- and third-party sources. It helps spot micro-segments and emerging demand spaces (eg. new occasions, sub-segments, servicing opportunities, etc.) to build new business models, optimize the product, pricing, promotion, and marketing activities.

• Forestall & Recommend Actions: AI assistants can scan all channels, markets, competitor actions, retailer actions, and self-assess to find opportunities and threats. Next, predictive models can evaluate complex interactions to explore numerous possibilities and suggest the best action to people based on their roles, owing to each market and the account relationship.

AI also helps to redefine businesses by automating manual, repetitive, and high-volume processes. Its learning capabilities allow it to self-optimize over time and reduce the work volume of employees. The technology’s deployment not only boosts employee productivity but also unlocks greater ROI for businesses.

• Growth Hacking Through Quick Test And Learn: AI systems evolve themselves by learning from experiences. Event analysis in RGM takes a futuristic approach towards learning about consumer behaviour. AI models bridge the gap between plan, execution, and results with the process of continuous learning using ‘recommend’, ‘act’, ‘measure’, and ‘learn’ methodology. RGM or related teams can conduct well-designed experiments in choicest markets, analyse the outcome, and roll out smart strategies across the business.
• Ongoing Feedback:It creates a loop mechanism for continuous learning model and recommendation improvements. The feedback loop ensures that the model keeps on updating itself without much human intervention.

It also helps in creating hyper-curated experiences. Because AI analyzes massive unstructured data such as photos, audio, video, etc., this helps in creating most relevant and personalized messaging and offers, and value-added services. This is while basing on consumer preferences in real-time.

AI-led RGM fosters sustainable success

Leveraging AI to thoroughly understand the consumer and reinvent relevance, CPG companies can develop a powerful capability. It can help them retain and expand their user-base, reduce costs, stand-out competitively, and drive new opportunities. Also, AI can improve their ever-evolving standards of performance by optimizing interactions and transactions – paving the way for never-ending growth.

Pricing and trade spend within Revenue Growth Management are some of the most powerful yet complex functions. If done well, they can help organizations win over not just their customers, but the market as well. So, prefer a solution provider that has a proven track record of RGM toolkit deployment and its subsequent scaling.

The post How artificial intelligence fuels revenue growth management appeared first on Artificial Intelligence.