Enabling Sustainable Agriculture: InstaDeep uses Cloud TPU v4
2647
Of your peers have already read this article.
3:30 Minutes
The most insightful time you'll spend today!
You are what you eat. We’ve all been told this, but the truth is what we eat is often more complex than we are – genetically at least. Take a grain of rice. The plant that produces rice has 40,000 to 50,000 genes, double that of humans, yet we know far more about the composition of the human genome than of plant life. We need to close this knowledge gap quickly if we are to answer the urgent challenge of feeding 8 billion people, especially as food security around the globe is likely to worsen with climate change.
For this reason, AI company InstaDeep has teamed up with Google Cloud to train a large AI model with more than 20 billion parameters on a dataset of reference genomes for cereal crops and edible vegetables, using the latest generation of Google’s Tensor Processing Units (Cloud TPU v4), which is particularly suited for training efficiency at scale. Our aim is to improve food security and sustainable agriculture by creating a tool that can analyze and predict plants’ agronomic traits from genomic sequences. This will help identify which genes make some crops more nutritious, more efficient to grow, and more resilient and resistant to pests, disease and drought.
Genomic language models for sustainable agriculture
Ever since farming began, we have been, directly or indirectly, trying to breed better crops with higher yields, better resilience and, if we’re lucky, better taste too. For thousands of years, this was done by trial and error, growing crops year-on-year while trying to identify and retain only the most beneficial traits as they naturally arise from evolutionary mutations. Now that we have access to the genomic sequences of plants, we hope to directly identify beneficial genes and predict the effect of novel mutations.
However, the complexity of plant genomes often makes it difficult to identify which variants are beneficial. Revolutionary advances in machine learning (ML) can help to understand the link between DNA sequences and molecular phenotypes. This means we now have precise and cost-effective prediction methods to help us close the gap between genetic information and observable traits. These predictions can help identify functional variants and accelerate our understanding of which genes link to which traits – so we can make better crop selections.
Moreover, thanks to the vast library of available crop genetic sequences, training large models on hundreds of plant genomes means we can transfer the knowledge from thoroughly-studied species to those that are less understood but important for food production – especially in developing countries. And by doing this digitally, AI can quickly map and annotate the genomes of both common and rare crop variants.
One of the major limitations of traditional ML methods for plant genomics has been they mostly rely on supervised learning techniques. They need labeled data. Such data is scarce and expensive to collect, severely limiting these methods. Recent advances in natural language processing (NLP), such as Transformer architectures and BERT-style training (Bidirectional Encoder Representations from Transformers), allow scientists to train massive language models on raw text data to learn meaningful representations. This unsupervised learning technique changes the game. Once learned, the representations can be leveraged to solve complex regression or classification tasks – even when there is a lack of labeled data.
InstaDeep partners with Google Cloud to train the new generation of AI models for genomics on TPUs
Researchers have demonstrated that large language models can be especially effective in proteomics. To understand how this works, imagine reading amino acids as words and proteins as sentences. The treasure trove of raw genomics data – in sequence form – inspired InstaDeep and Google Cloud to apply similar technologies on nucleotides, this time reading them as words and chunks of genomes as sentences.
Moreover, the representations that the system learned improved in line with the size of the models and datasets, NLP research studies showed. This finding led InstaDeep researchers to train a set of increasingly larger language models on genomics datasets ranging from 1 billion to 20 billion parameters.
- Models of 1 billion and 5 billion parameters were trained on a dataset comprising the reference genomes for several edible plants, including fruit, cereal and vegetables for a total of 75 billion nucleotides.
- The training dataset must increase in the same proportion as the model capacity, recent work has shown. Thus, we created a larger dataset gathering all reference genomes available on the National Center for Biotechnology Information (NCBI) database including human, animal, non-edible plant and bacteria genomes. This dataset, which we used to train a 20-billion-parameter Transformer model, comprised 700 billion tokens, exceeding the size of most datasets typically used for NLP applications, such as the Common Crawl or Wikipedia dataset.
- Both teams announced that the 1 billion-parameter model will be shared with the scientific community to further accelerate plant genomics research.
The compact and meaningful representations of nucleotide sequences learned by these models can be used to tackle molecular phenotype prediction problems. To showcase their ability, we trained a model to predict the gene function and gene ontology (i.e. a gene’s attribute) for different edible plant species.
Early results have demonstrated that this model can predict these characteristics with high accuracy – encouraging us to look deeper at what these models can tell us. Based on these results, we decided to annotate the genomes of three plant species with considerable importance for many developing countries: cassava, sweet potato, and yam. We are working on making these annotations freely available to the scientific community and hope that these will be used to further guide and accelerate new genomic research.
Overcoming scaling challenges with massive models and datasets with Cloud TPUs
The compute requirement for training our 20 billion-parameter model with billions of tokens is massive. While modern accelerators offer impressive peak performance per chip, to utilize this performance often requires tightly coupled hardware and software optimizations. Moreover, maintaining this efficiency when scaling to hundreds of chips presents additional system design challenges. The Cloud TPU’s tightly-coupled hardware and software stack is especially well suited to such challenges. The Cloud TPU software stack is based on the XLA Compiler which offers out-of-the-box optimizations (such as compute and communication overlap) and an easy programming model for expressing parallelism.
We successfully trained our large models for genomics by leveraging Google Tensor Processing Units (TPUv4). Our code is implemented with the JAX framework. JAX provides a functional programming-based approach to express computations as functions that can be easily parallelized using JAX APIs powered by XLA. This helped us to scale from a single host (four chips) configuration to a multi-host configuration without having to tackle any of the system design challenges. The TPU’s cost-effective inter- and intra-communication capabilities led to an almost linear scaling between the number of chips and training time. This allowed us to train the models quickly and efficiently on a grid of 1024 TPUv4 cores (512 chips).
Conclusion
Ultimately, our hope is that the functional characterization of genomic variants predicted by deep learning models will be critical to the next era in agriculture, which will largely depend on genome editing and analysis. We envisage that novel approaches, such as in-silico mutagenesis – the assessment of all possible changes in a genomic region by a computer model – will be invaluable in prioritizing mutations that improve plant fitness and guiding crop improvements. Attempting similar work in wet-lab experiments would be difficult to scale and nearly impossible in nature. By making our current and future annotations available to the research community, we also hope to help democratize breeding technologies so that they can benefit all of global agriculture.
Further Reading
To learn more about the unique features of Cloud TPU v4 hardware and software stack we encourage readers to explore Cloud TPU v4 announcement. To learn more about scaling characteristics, please see this benchmark and finally we recommend reading PJIT Introduction to get started with JAX and SPMD parallelism on Cloud TPU.
This research was made possible thanks to the support of Google’s TPU Research Cloud (TRC) Program which enabled us to use the Cloud TPUv4 chips that were critical to this work.
Boost Your ML Training Speed with GKE’s NCCL Fast Socket
888
Of your peers have already read this article.
1:30 Minutes
The most insightful time you'll spend today!
Large Machine Learning (ML) models – such as large language models, generative AI, and vision models – are dramatically increasing the number of trainable parameters and are achieving state-of-the-art results. Increasing the number of parameters results in the model being too large to fit on a single VM instance thus demands distributed compute to spread the model across multiple nodes. Google Kubernetes Engine (GKE) has built-in support for NCCL Fast Socket, to help improve the time to train large ML models with distributed, multi-node clusters.
Enterprises are looking for faster and cheaper performance to train their ML models. With distributed training, communicating gradients across nodes is a performance bottleneck. Optimizing inter-node latency is critical to reduce training time and costs. Distributed training uses collective communication as a transport layer over the network between the multiple hosts. Collective communication primitives such as all-gather, all-reduce, broadcast, reduce, reduce-scatter, and point-to-point send and receive are used in distributed training in Machine Learning.
The NVIDIA Collective Communication Library (NCCL) is commonly used by popular ML frameworks such as TensorFlow and PyTorch. It is a highly optimized implementation for high bandwidth and low latency between NVIDIA GPUs. Google developed a proprietary version of NCCL called NCCL Fast Socket to optimize performance for deep learning on Google Cloud.
NCCL Fast Socket uses a number of techniques to achieve better and more consistent NCCL performance.
- Use of multiple network flows to attain maximum throughput. NCCL Fast Socket introduces additional optimizations over NCCL’s built-in multi-stream support, including better overlapping of multiple communication requests.
- Dynamic load balancing of multiple network flows. NCCL can adapt to changing network and host conditions. With this optimization, straggler network flows will not significantly slow down the entire NCCL collective operation.
- Integration with Google Cloud’s Andromeda virtual network stack.This increases overall network throughput by avoiding contentions in virtual machines (VMs).
We tested (NVIDIA NCCL tests) the performance of NCCL Fast Socket vs NCCL on various machine shapes with 2 node GKE clusters.
The following chart shows the results. For each machine shape, the NCCL performance without Fast Socket is normalized to 1. In each case, using NCCL Fast Socket demonstrated increased performance in a range of 1.3 to 2.6 times faster internetwork communication speed.
As a built-in feature, GKE users can take advantage of NCCL Fast Socket without changing or recompiling their applications, ML frameworks (such as TensorFlow or PyTorch), or even the NCCL library itself. To start using NCCL Fast Socket, create a node pool that uses the plugin with the --enable-fast-socket and --enable-gvnic flags. You can also update an existing node pool using gcloud container node-pools update.
gcloud container node-pools create NODEPOOL_NAME \
--accelerator type=ACCELERATOR_TYPE, count=ACCELERATOR_COUNT \
--machine-type=MACHINE_TYPE \
--cluster=CLUSTER_NAME \
--enable-fast-socket \
--enable-gvnicTo achieve better network throughput with NCCL, Google Virtual NICs (gVNICs) must be enabled when creating VM instances. For detailed instructions on how to use gVNICs, please refer to the gVNIC guide.
To verify that NCCL Fast Socket has been enabled, view the kube-system pods:
kubectl get pods -n kube-system
And the output should b similar to:
NAME READY STATUS RESTARTS AGE
fast-socket-installer-qvfdw 2/2 Running 0 10m
fast-socket-installer-rtjs4 2/2 Running 0 10m
fast-socket-installer-tm294 2/2 Running 0 10mTo learn more visit GKE NCCL Fast Socket documentation. We look forward to hearing how NCCL Fast Socket improves your ML Training experience on GKE.
You Can Quantify and Maximize Value of Your Org’s AI/ML and Analytics Teams!
4420
Of your peers have already read this article.
1:30 Minutes
The most insightful time you'll spend today!
Investing in Artificial Intelligence (AI) can bring a competitive advantage to your organization. If you’re in charge of an AI or Data Science team, you’ll want to measure and maximize the value that you’re providing. Here is some advice from our years of experience in the field.
A checklist to embark on a project:
As you embark on projects we’ve found it’s good to have the following areas covered:
- Have a customer. It’s important to have a customer for your work, and that they agree with what you’re trying to achieve. Be sure to know what value you’re delivering to them.
- Have a business case. This will rely on estimates and assumptions, and may take no more than a few minute’s work. You should revise this, but always know what justifies your team’s effort, and what you (and your customer) expect to get in return.
- Know what process you will change or create. You’ll want to put your work in production, so you have to be clear about what business operations are changing or created around your work and who needs to be involved to make it happen
- Have a measurement plan. You’ll want to show that ongoing work is impacting some relevant business indicator. Measure and show incremental value. The goal of these measurements is to establish what has changed because of your project that would otherwise not have changed. Be sure to account for other factors like seasonality or other business changes that may affect your measurements.
- Use all the above to get your organization’s support for your team and your work.
What measures to use?
As you start the work, what measures and indicators can you use to show that your team’s work is useful for your organization?
How many decisions you make. A major function of ML is to automate and optimize decisions: which product to recommend, which route to follow, etc. Use logs to track how many decisions your systems are making.
Changes to revenue or costs. Better and quicker decisions often lead to increased revenue or savings. If possible, measure it directly, otherwise estimate it (for example fuel costs saved from less distance traveled, or increased purchases from personalized offers).
As an example, the Illinois Department of Employment Security is using Contact Center AI to rapidly deploy virtual agents to help more than 1 million citizens file unemployment claims. To measure success the team tracked the two outcomes: (1) the number of web inquiries and voice calls they were able to handle, and (2) the overall cost of the call center after the implementation. Post implementation, they were able to observe more than 140,000 phone and web inquiries per day and over 40,000 after-hours calls per night. They also anticipate an estimated annual cost savings of $100M based on an initial analysis of IDES’s virtual agent data (see more in the link to case study).
Implementation costs. The other side of increased revenue or savings, is to put your achievements in the context of how much they cost. Show the technology costs that your team incurs and, ideally, how you can deliver more value, more efficiently.
How much time was saved. If the team built a routing system then it saved travel time, if it built an email classifier then it saved reading time, etc. Quantify how many hours were given back to the organization thanks to the efficiency of your system.
In the medical field, quicker diagnostics matter. Johns Hopkins University’s Brain Injury Outcomes (BIOS) Division has focused on studying brain hemorrhage aiming to improve medical outcomes. The team identified the time to insights as a key metric in measuring business success. They experimented with a range of cloud computing solutions like Dataflow, Cloud Healthcare API, Compute Engine, and AI Platform for distributed training to accelerate iterations. As a result, in their recent work they were able to accelerate insights from scans from approximately 500 patients from 2,500 hours to 90 minutes.
How many applications your team supports. Some of your organization’s operations don’t use ML (say reconciling financial ledgers) but others do. Know how many parts of your organization benefit from the optimization and automation your team builds.
User experience. You may be able to measure your customer’s experience: fewer complaints, better reviews, reduced latency, more interactions, etc. This is valid both for internal and external stakeholders. At Google we measure usage and regularly ask for feedback on any internal system or process.
One of our customers, The City of Memphis, is using VisionAI and ML to tackle a common but very challenging issue: identifying and addressing potholes. The implementation team identified the percentage increase of potholes identified as one of the key metrics along with accuracy and cost savings. The solution captures video footage from it’s public vehicles and leverages Google Cloud capabilities like Compute Engine, AI Platform, and BigQuery to automate the review of videos. The project increased pothole detection by 75% with over 90% accuracy. By measuring and demonstrating these outcomes, the team proved the viability of a cost-effective, cloud-based machine learning model and is looking into new applications of AI and ML that will further improve city services and help it build a better future for its 652,000 residents.
Acknowledgements
Filipe and Payam would like to thank our colleague and co-author Mona Mona (AI/ML Customer Engineer, Healthcare and lifesciences) who contributed equally to the writing.
How Connected-Stories Uses BigQuery and AI/ML to Craft Personalized Ad Experiences
4010
Of your peers have already read this article.
4:00 Minutes
The most insightful time you'll spend today!
Editor’s note: The post is part of a series highlighting our awesome partners, and their solutions, that are Built with BigQuery
In the field of producing engaging video content such as ads, many marketers ignore the power of data to improve their creative efforts to meet the consumers’ need for personalized messages. The demand for creative tech to efficiently personalize is real as marketers need personalized video Ads to reach their audience with the right message at the right time. Data, Insights and Technology are the main ingredients to deliver this value while ensuring security and privacy requirements are met. The Connected-Stories team partnered with Google Cloud to build a platform for Ad personalization. Google Data Cloud and BigQuery are at the forefront to assimilate data, leverage ML models, create personalized ads, and capitalize on real-time intelligence as the core features of the Connected-Stories NEXT platform.
Connected-Stories NEXT is an end-to-end creative management platform to develop, serve, and optimize interactive video and display ads that scale across any channel. The platform ingests first-party data to create custom ML models, measure numerous third-party data points to help brands develop unique customer journeys and create videos that their data signals can drive. An intelligent feedback loop passes real-time data back, enabling brands to make data-driven and actionable video ads that take the brand’s campaigns to the next level.
The core use case of the NEXT platform revolves around collecting user’s interaction data and optimizing for precision and speed to create an actionable Ad experience that is personalized for each user. The platform processes complex data points to create interactive data visualizations that allow for accurate analysis. The platform uses Vertex AI to access managed tools, workflows, and infrastructure to build, deploy, and scale ML models that have improved the accuracy to identify segments for further analysis.
The platform ingests 200M data events with peaks and valleys of activity. These events are processed to generate dashboards that enable users to visualize metrics based on filters in real-time. These dashboards have high performance requirements in terms of a responsive user interface under constantly changing data dimensions.
Google Cloud’s serverless stack coupled with limitless data cloud infrastructure has been the core to the NEXT platform’s data-driven innovation. The growing volume of data ingested, streamed and processed were scaled uniformly across the compute, storage and analytical layers of solution. A lean development team at Connected-Stories were able to focus all-in on the solution, while the serverless stack scaled, lowered attack service in terms of security and optimized the cost footprint through pay-as-you-go features.
BigQuery has been the backbone to support the vast amounts of data spreading over multiple geos resulting in workloads running at petabyte scale. BigQuery’s fully managed serverless architecture, real-time streaming, built-in machine learning and rich business intelligence capabilities distinguishes itself from a cloud data warehouse. It is the foundation needed to approach data and serve users in an unlimited number of ways. For an application with zero tolerance for failure, given its fully managed nature, BigQuery handles replication, recovery, data distributed optimization and management.
The platform’s requirements include the need for low maintenance, constantly ingesting and refreshing data and smart-tuning of aggregated data. These capabilities can be implemented by BigQuery’s materialized views feature. Materialized views are useful for precomputed views that regularly cache query results for better performance. These views possess the innate feature to read only the delta change from base tables and calculate the up-to-date aggregations. Materialized views impart faster outputs and consume fewer resources while reducing the cost footprint.
Some key considerations in using Google cloud and focusing on the Serverless stack include: quick onboarding to development, prototyping in short sprints and ease of preparing data in a rapidly changing environment. Typical considerations around low code / no code include data transformation, aggregation and reduced deployment time. These considerations are fulfilled through using serverless capabilities within Google Cloud such as PubSub, Cloud Storage, Cloud Run, Cloud Composer, Dataflow and BigQuery as described in the Architecture diagram below. The use of each of these components and services are described below.
- Input/Ingest: At a high-level, microservices hosted in Cloud Run collect and aggregate incoming Ads events.
- Enrichment: The output of this stage is a Pub-Sub message enriched with more attributes based on a pre-configured campaign.
- Store: a Cloud Dataflow streaming job to create text files in Cloud Storage buckets.
- Trigger: Cloud Composer triggers the spark jobs based on text files to process and group them to produce desired output as one record per impression, a logical group of events.
- Deploy: Cloud Build is then used to automate all deployments.
Thus far, all Google cloud managed services work together to ingest, store and trigger the orchestration, all of which are scalable based on configurations including autoscaling capabilities.
- Visualization: A visualization tool reads data from BigQuery to compute pre-aggregations required for each dashboard.
- Data Model Evolution considerations: Though the solution served the purpose of creating pre-aggregations, as the data model evolved by adding a column or creating a new table, it led to recreating pre-aggregations and querying the data again. Alternatively, creating aggregate tables as an extra output of current ETLs seemed like a viable option. However, this would increase the cost and complexity of jobs. A similar situation to reprocess or update aggregated tables would occur as data is updated.
Precomputed views of data that is periodically cached are critical to reach the audience with the right message at the right time.
- Performance: In order to increase the performance of the platform, we need to have regularly precomputed views of the data, cached .
- Materialized Views: Consumers of these views needed faster response times, to consume fewer resources and output only the changes in comparison to a base table. BigQuery Materialized views were used to solve this very requirement. Materialized views have been highly leveraged to optimize the design resulting in lesser maintenance and access to fresh data with high performance with a relatively low technical investment in creating and maintaining SQL code.
- Dashboards: Application dashboards pointing to the Materialized views are highly performant and provide a view into fresh data.
- Custom Reports with Vertex AI Notebooks: Vertex AI notebooks directly read data from BigQuery to produce custom reports for a subset of customers. Vertex AI has been hugely beneficial to data analysts, where an environment with pre-installed libraries simplifies the readiness to use. Vertex AI Workbench notebooks are used to share these reports within the team allowing them to work always on the cloud without having the need to download data at any time. Besides, it increases the velocity to develop and test ML models faster.
The NEXT platform has yielded benefits such as customers having the ability to create unique consumer journeys powered by AI / ML personalization triggers, using first-party data and business intelligence tools to capitalize on real-time creative intelligence, which is a dashboard to measure campaign performance for cross-functional teams to analyze the impact of Ad content experience at a granular level. All of these while ensuring controlled access to data to enrich data without moving across clouds. The NEXT platform can keep up with increased demands for agility, scalability and reliability through the underlying usage of Google Cloud.
Partnering with Google, in the context of the Google Built with BigQuery program has surfaced the differentiated value in areas of creating interactive personalized Ads by using real-time data. In addition, by sharing this data across organizations as assets, ML models have fueled higher levels of innovation. Connected-Stories plan to deepen the penetration into the entire spectrum of services offered in the AI/ML area to enhance core functionality and provide newer capabilities to the platform.
Click here to learn more about Connected-Stories NEXT Platform capabilities.
The Built with BigQuery Advantage for ISVs
Through Built with BigQuery, launched in April ‘22 as part of Google Data Cloud Summit, Google is helping tech companies like Connected-Stories co-innovate in building applications that leverage Google’s data cloud with simplified access to technology, helpful and dedicated engineering support, and joint go-to-market programs. Participating companies can:
- Get started fast with a Google-funded, pre-configured sandbox.
- Accelerate product design and architecture through access to designated technical experts from the ISV Center of Excellence who can share insights from key use cases, architectural patterns, and best practices encountered in the field.
- Amplify success with joint marketing programs to drive awareness, generate demand, and increase adoption.
The Google Data Cloud spectrum of products and specifically BigQuery give ISVs the advantage of a powerful, highly scalable data warehouse that’s integrated with Google Cloud’s open, secure, sustainable platform. And with a huge and expanding partner ecosystem and support for multi-cloud, open source tools and APIs, Google provides technology companies the portability and extensibility they need to avoid data lock-in and exercise choice.
We thank the Google Cloud and Connected-Stories team members who co-authored the blog: Connected-Stories: Luna Catini, Marketing Director, Google: Sujit Khasnis, Cloud Partner Engineering
How AI and ML Helps Interpret Baseball Fandom during this MLB Season
4549
Of your peers have already read this article.
1:30 Minutes
The most insightful time you'll spend today!
The game of baseball has no shortage of statistics — from batting average to exit velocity, strikeouts to wins above replacement. Among all sports, Major League Baseball (MLB) arguably contains the most analytical and data-driven participants and fan base. Subconsciously or viscerally, players and managers on the field and those following from anywhere are constantly assessing and making decisions based off of game play trends and expectations — whether a batter will come through with a hit in an important situation, when a pitcher should be pulled. Less analyzed, however, is what leads fans to become engaged with certain players or teams, and what factors drive their love of the game. This is the motivation behind the problem being posed by Major League Baseball in their Kaggle competition for Player Digital Engagement Forecasting. Can you use machine learning to deconstruct baseball fandom?
This competition asks you to predict measures of digital engagement for each active player on a daily basis during the MLB season. So, how large was the surge in fan interest after Joe Musgrove threw the first no-hitter in Padres history? Is Shohei Ohtani’s engagement higher when he pitches well, when he hits a monster home run…or when he does both? You’re provided a wealth of game, team and player information – detailed stats, awards, rosters, and transaction information – as well as social and digital engagement data as your inputs. Data scientists will recognize this as an exciting forecasting problem with both traditional regression and time series components, where having this input data just prior to the prediction date is critical to determining which players will receive the most engagement.
With so many variables in the game, there are an endless number of vectors which could possibly influence fan engagement. Eleven-time All-Star Miguel Cabrera delighted fans by hitting the first home run of the season – in the snow! Occasionally a lesser-known player like Musgrove or Carlos Rodón “wins the day” with an unlikely no-hitter. And sometimes just getting traded to an iconic franchise like the Yankees generates a ton of fan interest, like it did for Rougned Odor in early April.
As these examples show, a player’s digital engagement can be pretty dynamic during the season, with many different potential contributors to who is “trending” on a given day. How can you use data to uncover which factors are the most influential of engagement with each player’s digital content?
Ready to play ball? Check out the competition on Kaggle for all the details. $50,000 in prizes is up for grabs in two prize categories. The code competition puts your machine learning skills to the test, to see who can build the most accurate forecasting models to predict daily digital engagement for every active player. You’ll have until July 31st to build your models and then be evaluated on a future time frame, which will determine the winners. For data visualization and exploration experts out there, the explainability prizes give you an opportunity to analyze more broadly which factors, even those outside of what we’re providing directly, most influence digital engagement. You’ll be evaluated on how well you can use what the data is telling you to support your findings.
And if you’re looking to get started, we’ve provided an introductory video and some notebook tutorials, including a starting point for harnessing the power of Vertex AI through tools including Cloud Notebooks, Explainable AI, and Vizier.
With the second half of the season upon us, it’s an exciting time to be an MLB fan. With this Kaggle competition, it’s also a perfect opportunity to use data science to help understand baseball fandom and potentially earn some of your own accolades in the process. Step up to the plate!
Major League Baseball trademarks and copyrights are used with permission of Major League Baseball. Visit MLB.com.
How the City of Memphis Uses Technology to Identify 75 Percent More Potholes
7134
Of your peers have already read this article.
4:30 Minutes
The most insightful time you'll spend today!
At 340 square miles, the City of Memphis is among the largest in the United States in terms of land area. Memphis has over 6,800 lane-miles of city streets, enough to drive back and forth to Los Angeles four times. Keeping these streets well maintained and safe for citizens and visitors is a major priority for the city.
Lots of traffic, lots of roads, and a four-season climate prone to wintertime freeze-thaw-refreeze cycles means the opportunity for potholes. Although the city aims to fill potholes within five business days of notification, it can take longer, especially during winter and early spring. Last year, the city’s Public Works crews repaired some 63,000 potholes, only 20% of which were reported by residents. Approximately 32,000-man-hours each year are spent repairing potholes, with seasonal fluctuations requiring ten to twelve Street Maintenance crews working steadily during the winter months. Still, many went unreported, leading the city to flag pothole request resolution under “needs improvement” on its open data portal website.
Like many large cities, Memphis also struggles with vacant and blighted properties. Nearly 15,000 properties in Memphis are likely vacant, and city officials contend that many are owned by out-of-town investors who live elsewhere and do not take necessary restoration or maintenance steps. These properties can decrease the value of surrounding real estate and discourage new businesses and other residents from moving to an area. Citizen frustration and concerns over the number of blighted properties has made blight eradication a major focus of the City of Memphis.
Historically, residents reported potholes and blighted properties by calling 311, or more recently by using the Memphis 311 app. However, these reports only covered about 20 percent of the problems — often the worst cases. And by the time residents took the initiative to submit a 311 report, they usually weren’t feeling good about the situation.
Recognizing that potholes and vacant properties are often the most visible indicators of whether a city government is doing its job efficiently, Memphis Mayor Jim Strickland and CIO Mike Rodriguez began looking for ways they could apply technology to fix the problems. Mike approached Google for ideas, and Google recommended conducting a machine learning proof-of-concept (POC) with SpringML, a Google Cloud Partner.
“Memphis is focused on easy living, and we want to do everything we can to keep our citizens happy,” says Mike Rodriguez. “Working with Google and SpringML to reduce potholes and urban blight using machine learning and artificial intelligence was an easy decision.”
Bringing machine learning to city operations and budgets
The city’s goal is to detect potholes and abandoned properties by analyzing video footage of roads and residential properties. It wanted to classify potholes by width and depth, and share the information with workers who can repair them. For abandoned properties, it wanted to enable more strategic deployment of resources for homeowners citywide and take action to hold neglectful property owners accountable.
The POC began by training TensorFlow models for ML object detection using preconfigured AI Platform Deep Learning VM Images on Compute Engine. SpringML helped set up cameras and developed a user interface to collect pothole data and automate the 311 ticketing process.
Together, the teams analyzed 30 days of video from a moving city bus and high-resolution video from 360-degree cameras mounted to a code enforcement vehicle, overlaid with data from 311 reports. As the models were refined, accuracy quickly climbed from 50 percent to over 90 percent as models were taught to differentiate a pothole from a manhole cover or other object.
The city also imported routes, potholes, and paving data along with geolocation data from ArcGIS and Google Maps into BigQuery to better understand street conditions and the proximity of potholes to one another. BigQuery also analyzes city property records, tax records, 311 reports, and third-party survey data on-demand to predict where homes are starting to become run down and where neighborhood decay is most likely to occur. The SpringML team created a pilot analysis to begin vacant property protections and developed a user interface tool to interact with the model’s results.
“Google Cloud Platform made it possible for us to experiment with machine learning and artificial intelligence to help solve our city’s problems while working within the budget constraints of a municipal IT organization,” says Mike. “Google turned a ‘nice to have’ into a ‘let’s do this!'”
Identifying 75 percent more potholes
Memphis expects to substantially reduce the number of potholes on its streets, creating a better driving experience for residents and visitors alike. Because drivers won’t be as likely to swerve to miss a pothole, streets will be safer and friendlier to bicycles and scooters. Fewer potholes will also save the city between $10,000 and $20,000 annually in city claims that it pays out in cases where vehicle damage results from a pothole that was not addressed in a timely manner.
“Historically, Public Works has relied primarily upon Street Maintenance crews to proactively locate and fill potholes. As Memphis has over 6,800 lane-miles of public streets, it is a daunting task to reliably survey the entire system in an efficient and systematic way,” says Robert Knecht, Public Works Director for the City of Memphis. “The outcome of the data collected will be invaluable to Public Works so that it can ensure it is managing the city’s street system in a more proactive manner.”
Memphis will be able to better prioritize road maintenance based on condition and impact, increasing the efficiency of its Public Works road crews. Analyzing video of streets also gave the city visibility into issues it wasn’t previously aware of, such as curbs, gutters, and manhole covers that had been mistakenly paved over and need to be excavated. The ML process is easily transferrable to other concerns as well, helping the city identify illegal signs or spools of cable hanging on light posts that could be potentially unsafe.
Helping communities recover and thrive
Memphis is also having success in analyzing predictive trends to combat high rates of abandoned and blighted properties, surpassing 97.5 percent accuracy. “In the past, Public Works experimented with comprehensive, city-wide blight identification by using approximately 200 volunteers to survey and photograph over 237,000 city parcels. This effort was costly, took a long time to complete, and resulted in inconsistent data collection,” says Robert. “Blighted property conditions can change quickly in a city the size of Memphis. Now, with this new technology, Memphis will be able to make a significant difference in the efforts to proactively and comprehensively identify and manage blighted and substandard properties.”
Code Enforcement with better data-driven detection mechanisms enables the city to also identify cases where homeowners are not physically or financially able to keep up with the challenges of homeownership and make them aware of resources that are available to assist them. Memphis Code Enforcement can do a better job of finding people living in derelict properties that pose hazards to inhabitants’ health and safety, and help them fix those problems or find a new place to live.
“Using SpringML and Google Cloud Platform to detect indicators of vacant or blighted properties will help Memphis create safer neighborhoods that will be more attractive to businesses and home buyers,” says Mike. “Property values and employment will go up, crime will go down, and social services can be more focused and effective.”
Revolutionizing service delivery for citizens
Memphis is proving the viability of a cost-effective, cloud-based machine learning model that other cities can follow. The city is already looking into new applications of AI and ML that will further improve city services and help it build a better future for its 652,000 residents.
As part of his commitment to a transparent government, Memphis Mayor Jim Strickland created an open data policy that commits to releasing raw data and sharing it with citizens in a variety of downloadable formats. Going forward, this transparency will help citizens understand how their needs are being served and uncover new, innovative use cases for AI and ML.
“Our goal is to become a smart city, and technologies such as Google Cloud Platform and SpringML put us ahead of the game,” says Mayor Strickland. “Google understands data, and there isn’t a better company to help us analyze our data resources for actionable insights.”
More Relevant Stories for Your Company
Special Identity Parsers in Document AI eases Customer Verification and KYC Processes
If you’ve opened an account at a bank, applied for a government benefit, or provided a proof of age document on an ecommerce website, chances are you’ve had to share a physical or digital copy of a Driver’s License or a passport as proof of your identity. For businesses or
Navigating the AI Landscape: The Future of AI for ML Engineers
A podcast-style video series exploring how AI is shaping our future and how to prepare for changes. Developer advocate, Arwen Hauzhenga, shares his 10+ years of experience in machine learning and generative AI. He discusses the evolution of the field from data mining to data science and large-scale machine learning.
Transform Your Marketing Strategy with Tinyclues and Google Cloud CDP
Editor’s note: The post is part of a series highlighting our awesome partners, and their solutions, that are Built with BigQuery. What are Customer Data Platforms (CDPs) and why do we need them? Today, customers utilize a wide array of devices when interacting with a brand. As an example, think
BigQuery ML for Sentiment Analysis: How to Make the Most of Your Data
Introduction We recently announced BigQuery support for sparse features which help users to store and process the sparse features efficiently while working with them. That functionality enables users to represent sparse tensors and train machine learning models directly in the BigQuery environment. Being able to represent sparse tensors is a
