Applications | Page 25 of 66 | Locus Technologies

Predicting Water Quality with Machine Learning

At Locus Technologies, we’re always looking for innovative ways to help water users better utilize their data. One way we can do that is with powerful technologies such as machine learning. Machine learning is a powerful tool which can be very useful when analyzing environmental data, including water quality, and can form a backbone for competent AI systems which help manage and monitor water. When done correctly, it can even predict the quality of a water system going forward in time. Such a versatile method is a huge asset when analyzing data on the quality of water.

To explore machine learning in water a little bit, we are going to use some groundwater data collected from Locus EIM, which can be loaded into Locus Platform with our API. Using this data, which includes various measurements on water quality, such as turbidity, we will build a model to estimate the pH of the water source from various other parameters, to an error of about 1 pH point. For the purpose of this post, we will be building the model in Python, utilizing a Jupyter Notebook environment.

When building a machine learning model, the first thing you need to do is get to know your data a bit. In this case, our EIM water data has 16,114 separate measurements. Plus, each of these measurements has a lot of info, including the Site ID, Location ID, the Field Parameter measured, the Measurement Date and Time, the Field Measurement itself, the Measurement Units, Field Sample ID and Comments, and the Latitude and Longitude. So, we need to do some janitorial work on our data. We can get rid of some columns we don’t need and separate the field measurements based on which specific parameter they measure and the time they were taken. Now, we have a datasheet with the columns Location ID, Year, Measurement Date, Measurement Time, Casing Volume, Dissolved Oxygen, Flow, Oxidation-Reduction Potential, pH, Specific Conductance, Temperature, and Turbidity, where the last eight are the parameters which had been measured. A small section of it is below.

Alright, now our data is better organized, and we can move over to Jupyter Notebook. But we still need to do a bit more maintenance. By looking at the specifics of our data set, we can see one major problem immediately. As shown in the picture below, the Casing Volume parameter has only 6 values. Since so much is missing, this parameter is useless for prediction, and we’ll remove it from the set.

We can check the set and see that some of our measurements have missing data. In fact, 261 of them have no data for pH. To train a model, we need data which has a result for our target, so these rows must be thrown out. Then, our dataset will have a value for pH in every row, but might still have missing values in the other columns. We can deal with these missing values in a number of ways, and it might be worth it to drop columns which are missing too much, like we did with Casing Volume. Luckily, none of our other parameters are, so for this example I filled in empty spaces in the other columns with the average of the other measurements. However, if you do this, it is necessary that you eliminate any major outliers which might skew this average.

Once your data is usable, then it is time to start building a model! You can start off by creating some helpful graphs, such as a correlation matrix, which can show the relationships between parameters.

For this example, we will build our model with the library Keras. Once the features and targets have been chosen, we can construct a model with code such as this:

This code will create a sequential deep learning model with 4 layers. The first three all have 64 nodes, and of them, the initial two use a rectified linear unit activation function, while the third uses a sigmoid activation function. The fourth layer has a single node and serves as the output.

Our model must be trained on the data, which is usually split into training and test sets. In this case, we will put 80% of the data into the training set and 20% into the test set. From the training set, 20% will be used as a validation subset. Then, our model examines the datapoints and the corresponding pH values and develops a solution with a fit. With Keras, you can save a history of the reduction in error throughout the fit for plotting, which can be useful when analyzing results. We can see that for our model, the training error gradually decreases as it learns a relationship between the parameters.

The end result is a trained model which has been tested on the test set and resulted in a certain error. When we ran the code, the test set error value was 1.11. As we are predicting pH, a full point of error could be fairly large, but the precision required of any model will depend on the situation. This error could be improved through modifying the model itself, for example by adjusting the learning rate or restructuring layers.

You can also graph the true target values with the model’s predictions, which can help when analyzing where the model can be improved. In our case, pH values in the middle of the range seem fairly accurate, but towards the higher values they become more unreliable.

So what do we do now that we have this model? In a sense, what is the point of machine learning? Well, one of the major strengths of this technology is the predictive capabilities it has. Say that we later acquire some data on a water source without information on the pH value. As long as the rest of the data is intact, we can predict what that value should be. Machine learning can also be incorporated into examination of things such as time series, to forecast a trend of predictions. Overall, machine learning is a very important part of data analytics and the development of powerful AI systems, and its importance will only increase in the future.

What’s next?

As the technology around machine learning and artificial intelligence evolves, Locus will be working to integrate these tools into our EHS software. More accurate predictions will lead to more insightful data, empowering our customers to make better business decisions.

Infographic: 6 Benefits of EHS on AWS

In this infographic, we have outlined a few of the ways EHS programs benefit from having an AWS-hosted solution. Locus customers recently received these benefits as a result of moving our entire infrastructure to Amazon Web Services—the world’s leading cloud. Learn more about the move to AWS.

Artificial Intelligence and Environmental Compliance–Revisited–Part 4: AI, Big Data + Multi-Tenancy = The Perfect System

AI and Big Data to Drive EHS Decisions via Multi-tenant SaaS

With data and information streaming from devices like fire hydrants, there is little benefit from raw data, unless a company owning the data has a way to integrate the data into its record system and pair it with regulatory databases and GIS. That is where the advancement in SaaS tools and data sources mashups has helped set the stage for AI as a growing need.

Humans are not very good at analyzing large datasets. This is particularly true with data at the planetary level that are now growing exponentially to understand causes and fight climate change. Faced with a proliferation of new regulations and pressure to make their companies “sustainable” EHS departments keep adding more and more compliance officers, managers, and outside consultants, instead of investing in technology that can help them. Soon, they will be turning to AI technology to stay on top of the ever-changing regulatory landscape.

AI, in addition to being faster and more accurate, should make compliance easier. Companies spend too much time and effort on the comprehensive quarterly or annual reporting—only to have to duplicate the work for the next reporting period. The integrated approach, aided by AI, will automate these repetitive tasks and make it easier than just having separate analyses performed on every silo of information before having a conversation with regulators.

In summary, whether it is being used to help with GHG emissions monitoring and reporting, water quality management, waste management, incident management, or other general compliance functions, AI can improve efficiency, weed out false-positive results, cut costs and make better use of managers’ time and company resources.

Another advantage of AI, assuming it is deployed properly, concerns its inherent neutrality on data evaluation and decision making. Time and time again we read in the papers about psychological studies and surveys that show people on opposite sides of a question or topic cannot even agree on the “facts.” It should not be surprising then to find that EHS managers and engineers are often limited by their biases. As noted in the recent best-seller book by Nobel Memorial Prize in Economics laureate Daniel Kahneman, “Thinking, Fast and Slow,” when making decisions, they frequently see what they want, ignore probabilities, and minimize risks that uproot their hopes. Even worse, they are often confident even when they are wrong. Algorithms with AI built-in are more likely to detect our errors than we are. AI-driven intelligent databases are now becoming powerful enough to help us reduce human biases from our decision-making. For that reason, large datasets, applied analytics, and advanced charting and data visualization tools, will soon be driving daily EHS decisions.

In the past, companies almost exclusively relied upon on-premise software (or single-tenant cloud software, which is not much different from on-premise). Barriers were strewn everywhere. Legacy systems did not talk to one another, as few of the systems interfaced with one another. Getting data into third-party apps usually required the information to be first exported in a prescribed format, then imported to a third-party app for further processing and analysis. Sometimes data was duplicated across multiple systems and apps to avoid the headache of moving data from one to another. As the world moves to the multi-tenant SaaS cloud, all this is now changing. Customers are now being given the opportunity to analyze not just their company’s data, but data from other companies and different but potentially related and coupled categories via mashups. As customers are doing so, interesting patterns are beginning to emerge.

The explosion of content—especially unstructured content—is an opportunity and an obstacle for every business today.

The emergence of artificial intelligence is a game-changer for enterprise EHS and content management because it can deliver business insights at scale and make EHS compliance more productive. There are numerous advantages when you combine the leading multi-tenant EHS software with AI:

Ability to handle the explosion of unstructured content where legacy on-premise EHS solutions can’t.
AI can organize, illuminate, and extract valuable business insights if all your content is managed in one secure location in the cloud.
Locus helps you take advantage of best-of-breed AI technologies from industry leaders and apply them to all your content.

We are seeing in the most recent NAEM white paper, Why Companies Replace Their EHS&S Software Systems, that people want the ability to integrate with other systems as a top priority. Once the ability to share/consolidate data is available, AI is not far behind in the next generation of EHS/Water Quality software.

This concludes the four-part blog series on Big Data, IoT, AI, and multi-tenancy. We look forward to feedback on our ideas and are interested in hearing where others see the future of AI in EHS software – contact us for more discussion or ideas! Read the full Series: Part One, Part Two, Part Three.

Locus Technologies goes all-in on AWS

SAN FRANCISCO, Calif., 23 July 2019 — Locus Technologies (Locus), the market leader in multi-tenant SaaS water quality, environmental compliance, and sustainability management, today announced that it is going all-in on Amazon Web Services, Inc. (AWS), moving its entire infrastructure to the world’s leading cloud. By moving its flagship product EIM (Environmental Information Management) to AWS this month, Locus will complete its transition to AWS. Locus previously moved its Locus Platform (LP) to AWS in 2018.

EIM is the world’s leading water quality management software used by many Fortune 500 companies, water utilities, and the US Government since 1999. Among its many features, EIM delivers real-time tools to ensure that water utilities deliver clean water to consumers’ taps and don’t discharge contaminated wastewater above allowable limits to groundwater or surface water bodies like streams, lakes, or oceans.

EIM generates big data, and with over 500 million analytical records at over 1.3 million locations worldwide, it is one of the largest centralized, multi-tenant water quality management SaaS systems in the world. With anticipated growth in double digits stemming from the addition of streaming data from sensors and many IoT monitoring devices, Locus needed to have a highly scalable architecture for its software hosting. The unmatched performance and scalability of AWS’s offerings are just the right match for powering Locus’ SaaS.

Because of the scope of its applications, Locus is expecting to leverage the breadth and depth of AWS’s services (including its database systems, serverless architecture, IoT streaming, blockchain, machine learning, and analytics) to automate and enhance the on-demand EHS compliance, sustainability, facility, water, energy, and GHG management tools that Locus’ software provides to its customers.

Running on AWS’s fault-tolerant and highly performant infrastructure will help support Locus’s everyday business, and will scale easily for peak periods, where reporting demand such as GHG calculation engine or significant emissions incidents like spills can skyrocket scalability demand.

By leveraging Amazon CloudFront, Amazon Virtual Private Cloud (Amazon VPC), Amazon Elastic Kubernetes Service (Amazon EKS) and AWS Lambda, Locus is migrating to a microservices architecture to create more than 150 microservices that independently scale workloads while reducing complexity in the cloud, thereby enhancing every element of the customer cloud experience. Locus built a data lake on Amazon Simple Storage Service (Amazon S3) and will leverage Amazon Redshift to analyze the vast amount of data it is storing in the cloud, delivering insights and predictive analytics that uncover chemicals trending patterns and predict future emissions releases at various locations.

Locus intends to leverage AWS IoT services and Amazon Managed Blockchain by building a new native integration to help businesses generate value from the millions of events generated by connected devices such as real-time environmental monitoring sensors and environmental treatment systems controls. AWS IoT is a set of cloud services that let connected devices easily and securely interact with cloud applications like EIM and Locus Platform and other devices. Locus IoT Cloud on AWS allows customers to experience real-time emissions monitoring and management across all their connected sensors and devices. And for customers who want to allow multiple parties to transact (e.g. GHG trading) without a trusted central authority, AWS provides a fully managed, scalable blockchain service. Amazon Managed Blockchain is a fully managed service makes it easy to setup, deploy, and manage scalable blockchain networks that Locus intends to use for emissions management and trading.

For example, a water utility company that maintains thousands of IoT-enabled sensors for water flow, pressure, pH, or other water quality measuring devices across their dispersed facilities and pipeline networks will be able to use Locus IoT on AWS to ingest and manage the data generated by those sensors and devices, and interpret it in real time. By combining water sensor data with regulatory databases, water utility companies will be able to automatically create an emergency shutdown if chemical or other exceedances or device faults are detected and as such, will be better prepared to serve their customers and environment.

By combining the powerful, actionable intelligence in EIM and rapid responsiveness through Locus Platform with the scalability and fast-query performance of AWS, customers will be able to analyze large datasets seamlessly on arrival in real time. This will allow Locus’ customers to explore information quickly, find insights, and take actions from a greater variety and volume of data—all without investing the significant time and resources required to administer a self-managed on-premises data warehouse.

“After 22 years in business, and after evaluating AWS for a year with our Locus Platform, we decided to switch and continue all our business on AWS. We are taking advantage of their extensive computing power, depth and breadth of services and expertise to develop an effective cloud infrastructure to support our growing business and goal of saving the planet Earth by providing and managing factual information on emissions management, all the while reducing operational costs of Locus’ customers,” said Neno Duplan CEO of Locus. “By operating on AWS, we can scale and innovate quickly to provide new features and improvements to our services – such as blockchain-based emissions management – and deliver exceptional scalability for our enterprise customers. With AWS, we don’t have to focus on the undifferentiated heavy lifting of managing our infrastructure, and can concentrate instead on developing and improving apps and services.”

“By organizing and analyzing environmental, sustainability, and water quality information in the cloud, Locus is helping organizations to understand the impact of climate change on drinking water,” said Mike Clayville, Vice President, Worldwide Commercial Sales at AWS. “AWS’s unmatched portfolio of cloud services, proven operational expertise, and unmatched reliability will help Locus to further automate environmental compliance for companies ranging from local water utilities to multinational manufacturing corporations, to federal government research agencies. ”By choosing to go all-in on AWS, Locus is able to innovate and expand globally, developing new solutions that will leverage comprehensive analytics and machine learning services to gain deeper insights and forecast sustainability metrics that will help deliver clean drinking water to consumers around the world.”

Read on GlobeNewswire

Artificial Intelligence and Environmental Compliance–Revisited–Part 3: Multi-Tenancy and AI

SaaS–Multi-Tenant Cloud Architecture

Multi-tenancy offers distinct benefits over traditional, single-tenant software hosting. A multi-tenant SaaS provider’s resources are focused on maintaining a single, current version of the application, rather than having its resources diluted in an attempt to support multiple software versions for its customers. If a provider is not using multi-tenancy, it may be hosting or supporting thousands of single-tenant customer implementations. By doing so, a provider cannot aggregate information across customers and extract knowledge from large data sets as every customer may be housed on a different server and possibly a different version of software. For these reasons, it is almost impossible and prohibitively expensive to deliver modern AI tools via single-tenancy.

Locus Multi-Tenant Software — View Infographic | Download White Paper

Multi-tenancy has other advantages as well. Because every customer is on the same version of the software and the same instance, machine-learning (a prerequisite for building an AI system) can happen more quickly as large datasets are constantly fed into a single system. A multi-tenant SaaS vendor can integrate and deploy new AI features more quickly, more frequently, and to all customers at once. Lastly, a single software version creates more of a sense of community among users and facilitates the customers’ ability to share their lessons learned with one another (if they chose to do that). Most of today’s vendors in the EH&S software space cannot offer AI, sustain their businesses, and grow unless they are a true multi-tenant SaaS provider. Very few vendors are.

AI

Almost 30 years after the publication of our paper on the hazardous data explosion, SaaS technologies combined with other advancements in big data processing are rising to the challenge of successful processing, analyzing, and interpreting large quantities of environmental and sustainability data. It is finally time to stop saying that AI is a promising technology of the future. A recent Gartner study indicates that about 20 percent of data will be created or gathered by computers by 2018. Six billion connected devices will acquire the ability to connect and share data with each other. This alone will fuel AI growth as we humans cannot interpret such massive amounts of data.

Gone are the days where EHS software was just a database. There are two factors that are fueling the adoption of AI technologies for water quality management and EHS compliance. First, there is a vast increase that we have mentioned of data that needs sorting and understanding (big data). Second, there is the move to true multi-tenant SaaS solutions, which enables the intake and dissection of data from multiple digital sources (streaming data) from multiple customers, all in real-time.

AI has entered the mainstream with the backing and advocacy of companies like IBM, Google, and Salesforce, who are heavily investing in the technology and generating lots of buzzes (and we are seeing the consequent talent war happening industry-wide). It is remarkable to observe how quickly AI is proliferating in so many verticals, as CBS’s 60 Minutes segment showed us.

For our purposes, let’s look at where AI is likely to be applied in the EHS space. The mission-critical problem for EHS enterprise software companies is finding solutions that both enhance compliance and reduce manual labor and costs. This is where AI will play a major role. So far, companies have largely focused on aggregating their data in a record system(s); they have done little to interpret that data without human interaction. To address the ever-changing growth in environmental regulations, companies have been throwing people at the problem, but that is not sustainable.

AI and natural language processing (NLP) systems have matured enough to read through the legalese of regulations, couple them with company’s monitoring and emissions data, and generate suggestions for actions based on relevant regulations and data. Take, for example; a CEMS installed at many plants to monitor air emissions in real-time. Alternatively, a drinking water supply system monitoring for water quality. In each of these systems, there are too many transactions taking place to monitor manually to ascertain which ones are compliant and which ones are not? I see no reason why similar algorithms that are used for computerized trading (as described in the recent best-seller “Flash Boys”) to trade stocks in fractions of a second cannot be used for monitoring exceedances and automatically shutting down discharges if there is an approaching possibility of emission exceedance. It is an onerous task to figure out every exceedance on a case-by-case basis. Intelligent databases with a built-in AI layer can interpret data on arrival and signal when emissions exceed prescribed limits or when other things go wrong. The main driver behind applying AI to EHS compliance is to lower costs and increase the quality of EHS compliance, data management, and interpretation, and ultimately, to avoid all fines for exceedances.

For example, a large water utility company has to wade through thousands of analytical results to look for outliers of a few dozen chemicals they are required to monitor to stay compliant. Some of these may be false-positives, but that still leaves some results to be investigated for outliers. Each of those investigations can take time. However, if a software algorithm has access to analytical results and can determine that the problem rests with a test in the lab, that problem can be solved quickly, almost without human interaction. That is powerful.

Combing through data and doing this by hand or via spreadsheet could take days and create a colossal waste of time and uncertainty. Hundreds of billable hours can be wasted with no guaranteed result. Using AI-driven SaaS software to determine what outliers need investigation allows compliance managers, engineers, and chemists to focus their expertise on just these cases and thus avoid wasting their time on the remaining ones that the AI engine indicates need no further examination.

Predictive analytics based on big data and AI will also make customer data (legacy and new) work harder for customers than any team(s) of consultants. A good analogy that came to me after watching 60 minutes is that the same way the clinical center in North Carolina used AI to improve cancer treatment for their patients, engineers and geologists can improve on selecting the site remedy that will be optimized for given site conditions and will lead to a faster and less expensive cleanup with minimum long-term monitoring requirements.

A final example where AI will be playing a role is in the area of enterprise carbon management. SaaS software is capable of integrating data from multiple sources, analyzing and aggregating it. This aggregated information can then be distributed to a company’s divisions or regulatory agencies for final reporting and validation/verification, all in real-time. This approach can save companies lots of time and resources. Companies will be able to access information from thousands of emission sources across the states, provinces, and even countries where their plants are located. Because each plant is likely to have its set of regulatory drivers and reporting requirements, these would have to be incorporated into the calculation and reporting engine. After data from each plant is uploaded to a central processing facility, the information would be translated into a “common language,” the correct calculation formulae and reporting requirements applied, and the results then returned to each division in a format suitable for reporting internally and externally.

Blockchain for EHS—Looking ahead

And finally, another emerging technology, blockchain, will further augment the power of AI for EHS monitoring and compliance. While blockchain is in its infancy, its decentralized approach coupled with AI will bring another revolution to EHS compliance and water monitoring.

Parts one, two, and four of this blog series complete the overview of Big Data, IoT, AI, and multi-tenancy. We look forward to feedback on our ideas and are interested in hearing where others see the future of AI in EHS software – contact us for more discussion or ideas!

Stories and conversations from this summer’s radiological workshop

Locus recently joined the nuclear power plant community in Orlando, FL for this year’s Radiological Effluents and Environmental Workshop. It’s always a pleasure to join other professionals in a space that encourages discussion, education, and awareness of industry processes and compliance.

Locus Technologies at the NEI Radiological Conference, Orlando, 2019

Bill Donaldson and Danny Moore of Locus Technologies.

Each conference we attend is an opportunity to learn. Whether talking with current or potential customers, it’s always fascinating to hear some of the success and horror stories experienced in their daily operations. We’ve summarized a few of those conversations below. And since REEW takes place in the summer, there’s a theme.

Version Island

Imagine you’ve spent years utilizing a certain feature of your radiological software. You’ve gone through the training process, the growing pains, and you are finally enjoying the fruits of that labor. Now imagine learning that the latest and greatest version being released has removed the feature that you’ve grown to rely on. You are now stuck on a version island. At this point, a costly and time consuming upgrade will cause more problems. Locus SaaS has no version numbers, meaning you will never need to upgrade.

Off the Grid

At one time, the simple columns and rows in Excel seemed to provide a sufficient solution to prepare your REMP sampling data for reports. However, when you need to transfer data between systems, or create more sophisticated reports, those grids begin to feel like prison bars. Maybe it’s time to go off the grid and deploy a more modern solution that can connect and work side by side with your existing tools.

Sunsetting (Decommissioning)

Closing a power plant is a long and involved process that many attendees were in the process of dealing with or will be in the near future. This operational change can be the motivation to rethink the way radiological data is sampled and managed. Some software packages can be too big for the job. Locus offers a modular approach where you only pay for what you need. Choosing which system tools are relevant to the type of data sampling and resources available can minimize implementation cost and increase productivity.

Serene Security

Many people we spoke with at REEW had serious security concerns. Locus takes those concerns seriously. We are SOC 1 and SOC 2 certified and have migrated our software to Amazon Web Services. All customer data is stored with AWS, one of the most advanced and secure cloud-hosting providers on the planet. Locus provides the ability to control user permissions, customizing access based on job duties. This provides a more granular approach to data security.

Making Plans

Using a sample planning application organizes sample events and allows for scheduling weeks, months, or years in advance. Many were interested in this powerful tool that is flexible enough to adapt when a reactor changes modes, allowing for one-time, ad-hoc samples. Mobile applications that integrate with planned samples and events minimize setup, ease data collection, speed up loading field data, and can expedite samples to the lab more efficiently.

Your feedback has helped Locus build a solution that makes it easy to manage all your facility’s data for RETS/REMP, helping you meet your NRC reporting requirements. We enjoyed speaking with everyone at REEW and we look forward to seeing you again next year!

Learn more about Locus for Nuclear.

About the author—Danny Moore, Locus Technologies

Mr. Moore has spent the last decade designing and marketing for enterprise SaaS systems. In his career at Locus, he leads a team of marketing professionals in branding, content creation, social media engagement, and email outreach. Mr. Moore enjoys attending conferences as a Locus brand ambassador and sharing any feedback gained to improve product development.

About the author—Bill Donaldson, Locus Technologies

Mr. Donaldson has 5 years experience in SaaS systems, performing Product Management and QA/QC of Locus Mobile iOS application and Locus’ Environmental Information Management system (EIM). While completing his B.S., Mr. Donaldson held several paid internships, where he configured a Relational GeoDatabase and a Database Management System (DBMS), for biological data entry.

Does your EHS software have a version number?

Freedom from product release tyranny

I love the article by Geoffrey Moore on the power of software as a service (SaaS) business model published on LinkedIn. In SaaS’s Real Triumph he writes: “by far the greatest contribution of SaaS is to free the enterprise from the tyranny of the product release model.”

He cites the operational burden, enterprise-wide distraction and associated cost to roll out an enterprise software and then the subsequent hesitation to repeat that when a new release of that software becomes available as that deployment model is not sustainable nor affordable. Companies spend big dollars buying and then deploying EHS software that they know will be outdated in just a few years. Only IT personnel benefits from that model as it may extend their employment for a few years before IT department goes out of business for good. Moore points out the painful truth, stating: “you have paid maintenance of 18 to 20% per year for anywhere from five to ten years for the express purpose of not availing yourself of the innovation created during that time period.”

Probably the main benefit of SaaS multi-tenancy (that is frequently overlooked during the software selection process) is no software versioning. This is because multi-tenant software typically provides a rolling upgrade program: incremental and continuous improvements. It is an entirely new architectural approach to software delivery and maintenance model. Companies have to develop applications from the ground up for multi-tenancy. Legacy client-server or single-tenant software cannot qualify for multi-tenancy. Let’s take a look at definitions:

Single-Tenant – A single instance of the software and supporting infrastructure serves a single customer. With single-tenancy, each customer has his or her own independent database and instance of the software. Essentially, there is no sharing happening with this option.

Multi-Tenant – Multi-tenancy means that a single instance of the software and its supporting infrastructure serves multiple customers. Each customer shares the software application and also shares a single database. Each tenant’s data is isolated and remains invisible to other tenants.

Benefits of SaaS Multi-Tenant Architecture

The multi-tenant architecture provides lower costs through economies of scale: With multi-tenancy, scaling has far fewer infrastructure implications than with a single-tenancy-hosted solution because new customers get access to the same software.

Shared infrastructure leads to lower costs: SaaS allows companies of all sizes to share infrastructure costs. Not having to provision or manage any infrastructure or software above and beyond internal resources enables businesses to focus on everyday tasks.

Ongoing maintenance and updates: Customers don’t need to pay costly upgrades to get new features or functionality.

Configuration can be done while leaving the underlying codebase unchanged: Single-tenant-hosted solutions are often customized, requiring changes to an application’s code. This customization can be costly and can make upgrades expensive and time-consuming because the upgrade might not be compatible with customers changes to the earlier software version.

Multi-tenant solutions are designed to be highly configurable so that businesses can make the application perform the way they want. There is no changing the code or data structure, making the upgrade process easy.

Multi-tenancy ensures that every customer is on the same version of the software. As a result, no customer is left behind when the software is updated to include new features and innovations. A single software version also creates a unique sense of community where customers and partners share knowledge, resources, and learning. Smart managers work with their peers and learn from them and what they are doing. A multi-tenant SaaS provider’s resources are focused on maintaining a single, current (and only) version of the application, rather than spread out in an attempt to support multiple software versions for customers. If a provider isn’t using multi-tenancy, it may be hosting thousands of single-tenant customer implementations. Trying to maintain that is too costly for the vendor, and those costs, sooner or later, become the customers’ costs.

A vendor who is invested in on-premise, hosted, and hybrid models cannot commit to providing all the benefits of a true SaaS model due to conflicting revenue models. Their resources are going to be spread thin, supporting multiple versions rather than driving innovation. Additionally, if the vendor makes the majority of their revenue selling on-premise software, it is difficult for them to fully commit to a true SaaS solution since the majority of their resources are allocated to supporting the on-premise software.

Before you engage future vendors for your enterprise EHS software, assuming you already decided to go with SaaS solution, ask these questions:

Does your software have version numbers?
Do you charge for upgrades and how often do you upgrade?

If the answer is yes to any of these two questions, you should not consider that vendor as they are not true multi-tenant SaaS. You should not select that vendor if they answer “we are in the process of switching to multi-tenancy.” Multi-tenancy train departed a long time ago, and no EHS vendor who is single-tenant is not going to make that switch in time to make it work.

And if they suddenly introduce a “multi-tenant” model (after selling an on-premises version for 10+ years) who in the world would want to migrate to that experimental cloud without putting the contract out to bid to explore a switch to well established and market-tested true multi-tenant providers? The first-mover advantage when it comes to multi-tenancy is a huge advantage for any vendor.

City of San Marcos, Texas selects Locus water quality compliance software

Locus will provide cloud environmental water quality software with GIS and mobile integration 

MOUNTAIN VIEW, Calif., 9 July 2019 — Locus Technologies, (Locus), the industry leader in water quality, EHS, sustainability, and compliance management software, is pleased to announce that the City of San Marcos, Texas Water/Wastewater Utility selected Locus Environmental Information Management (EIM) software to streamline water quality and wastewater management and compliance.

“With Locus’ water quality software we can streamline and modernize how we manage and report our critical water quality and wastewater data,” said Ron Riggins, San Marcos Water Quality Manager. “With an integrated mobile application, we will be able to access and react to field information faster than ever before.”

“By selecting Locus EIM water quality software, the City of San Marcos, Texas can simplify managing water and wastewater data and integrate with their existing GIS system. This will provide them a modern cloud solution with fully integrated mobile capabilities,” said Wes Hawthorne, President of Locus.

Artificial Intelligence and Environmental Compliance–Revisited–Part 2: IoT

More recently, big data has become more closely tied to IoT-generated streaming datasets such as Continued Air Emission Measurements (CEMS), real-time remote control and monitoring of treatment systems, water quality monitoring instrumentation, wireless sensors, and other types of wearable mobile devices. Add digitized historical records to this data streaming, and you end up with a deluge of data. (To learn more about big data and IoT trends in the EHS industry, please read this article: Keeping the Pulse on the Planet using Big Data.)

In the 1989 Hazardous Data Explosion article that I mentioned earlier, we first identified the limitation of relational database technology in interpreting data and the importance that IoT (automation as it was called at the time) and AI were going to play in the EHS industry. We wrote:

“It seems unavoidable that new or improved automated data processing techniques will be needed as the hazardous waste industry evolves. Automation (read IoT) can provide tools that help shorten the time it takes to obtain specific test results, extract the most significant findings, produce reports and display information graphically,”

We also claimed that “expert systems” (a piece of software programmed using artificial intelligence (AI) techniques. Such systems use databases of expert knowledge to offer advice or make decisions.) and AI could be possible solutions—technologies that have been a long time coming but still have a promising future in the context of big data.

“Currently used in other technical fields, expert systems employ methods of artificial intelligence for interpreting and processing large bodies of information.”

Although “expert systems” as a backbone for AI did not materialize as it was originally envisioned by researches, it was a necessary step that was needed to use big data to fulfil the purpose of an “expert”.

AI can be harnessed in a wide range of EHS compliance activities and situations to contribute to managing environmental impacts and climate change. Some examples of application include AI-infused permit management, AI-based permit interpretation and response to regulatory agencies, precision sampling, predicting natural attenuation of chemicals in water, managing sustainable supply chains, automating environmental monitoring and enforcement, and enhanced sampling and analysis based on real-time weather forecasts.

Parts one, three, and four of this blog series complete the overview of Big Data, IoT, AI and multi-tenancy. We look forward to feedback on our ideas and are interested in hearing where others see the future of AI in EHS software – contact us for more discussion or ideas!

Is PFAS Contamination in US Drinking Water Supply the Next Crisis?

In most cities in the US, drinking water quality conforms with the norms of the Safe Drinking Water Act, which requires EPA to set Maximum Contaminant Levels (MCL) for potential pollutants. Besides, the EPA’s Consumer Confidence Rule (CCR) of 1998 requires most public water suppliers to provide consumer confidence reports, also known as annual water quality reports, to their customers.

PFAS stands for “perfluoroalkyl and polyfluoroalkyl substances,” with the most important thing to know that this large group of synthetic chemicals includes perfluorooctanoic acid (PFOA) and perfluorooctane sulfonate (PFOS).

Not Regulated by EPA

When it comes to drinking water from the tap in the US, the phrase that fits concerning PFOA and PFOS is “caveat emptor” (buyer beware). The EPA has not regulated these chemicals. There are no federal regulations for PFOA and PFOS in drinking water in the US.

In May 2016, the EPA established a drinking water “health advisory” of 70 parts per trillion (ppt) for the combined concentrations of PFOA and PFOS. While that was a start, there’s a big difference between a health advisory and a regulation that has teeth. Moreover, many scientists consider 70 ppt too high a limit. Reportedly, the EPA is considering turning its 70 ppt health advisory into regulation.

Meanwhile, some states have stepped up to the plate to protect their residents and visitors better. In April 2019, for instance, the New Jersey Department of Environmental Protection (DEP) proposed maximum contamination levels (MCLs) of 14 ppt for PFOA and 13 ppt for PFOS in the state’s drinking water.

As a water consumer, you should be aware of this crisis, as it has the potential to affect both your health and wealth.

What are PFOA and PFOS?

This toxic couple has contaminated the drinking water supply in areas surrounding some industrial sites and military bases. They’re the most studied of the PFAS group because they’re the ones that have been produced in the most significant quantities in the United States, according to the US Environmental Protection Agency (EPA).

PFOA and PFOS, which repel water and stains of various types, have been used as coatings on fabrics and leather and in the production of stain-repellent carpeting and are found in firefighting foams — which have been used extensively on US military bases for decades — among other products. Moreover, some related polyfluoroalkyl compounds can be transformed into these chemicals in the environment, per the National Institutes of Health (NIH), with the Environmental Working Group (EWG) stating that some perfluorinated chemicals not only break down into PFOA in the environment but also can do so in the human body.

While PFOA and PFOS are no longer made in the US, that hardly matters in our global economy. Both are still produced internationally, which means they end up in our country via imports of consumer goods such as carpet, apparel, textiles, and paper and packaging.

Why all the concern about PFOA and PFOS?

These chemicals — dubbed “forever chemicals” because they’re persistent in the environment and the human body — have been linked to cancer, thyroid disease, weakened the immune system and liver function, low infant birth weight, and other health problems, according to many sources.

And this is what the EPA says: “There is evidence that exposure to PFAS can lead to adverse health outcomes in humans. If humans, or animals, ingest PFAS…the PFAS are absorbed and can accumulate in the body. PFAS stay in the human body for long periods. As a result, as people get exposed to PFAS from different sources over time, the level of PFAS in their bodies may increase to the point where they suffer from adverse health effects.”