AIH President’s Message

Your AIH leadership team and member volunteers are working hard on exciting initiatives for AIH. Thank you to all who have stepped forward to take on roles to help advance the mission of AIH. We rely on our members’ participation, and we are eager to engage more members in AIH activities. Even if not interested in taking on a leadership role for AIH or getting involved in various subcommittees or groups, we request all our members to be ambassadors for AIH and its certified members. Please contact me or others on our leadership team to get involved.

We are approaching an important pivot point for the focus of AIH’s leadership team. Much energy has been dedicated to improving fundamental processes for AIH over the past few years. While we continue our work to address challenges, changes are underway that we are confident will improve our processes. Examples include rollout of new online member application and database system, and upcoming solicitation for examination support services. Concurrently, we are advancing initiatives related to member engagement, along with collaboration and engagement with other organizations (e.g., American Water Resources Association (AWRA); Consortium of Universities for the Advancement of Hydrologic Science, Inc. (CUAHSI); etc.).

Noted in my previous message, we established a new Diversity, Equity, and Inclusion (DEI) Committee along with a new Webinars Subcommittee. Kudos to: Ed Baquerizo, PH; Megan Gehrke, PH; Ramanitharan Kandiah, PH; Amesha Morris, Matt Naftaly, PH; John Ramirez Avila, PH; and Michelle Woolfolk, PH, and along with AIH leadership team members (Sarah Erck, CMP; Salam Murtada, PH; and Julé Rizzardo, PH) for stepping up to lead AIH’s DEI initiatives. Our Webinars Subcommittee members include member volunteer, Mike Talbot, HIT, and AIH leadership team members (Sarah Erck; Yige Gao, PH; Salam Murtada, PH; and Brennon Schaefer, PH). We’re excited for the rollout of actions from these two groups over the next few months.

On a matter related to inclusion, our Executive Committee (EC) advanced an action earlier this year to eliminate the constraint of nominations for serving on AIH’s EC to only certified Professional Hydrologists (PH)–all certified members (PHs, Hydrologists-in-Training (HITs), and Hydrologic Technicians (HTs) may be nominated to serve for positions on the EC. Subsequently, Chance Fulk, HT III, was appointed as Treasurer, the first HT to serve on AIH’s EC.

Please look for upcoming announcements regarding membership engagement. We’re planning a virtual “meet and greet” event during September and, if all goes well, an in-person social event in Sacramento, California to ring in the New Water Year on September 30. I’m very excited for these events!

 

PS: Note deliberate effort to include AIH certified members’ acronyms with names. I’m calling on all AIH certified members, as ambassadors of AIH, to take pride and flaunt your AIH acronym. Be HIT-, HT-, and PH-proud!

Sincerely,

Jamil S. Ibrahim PH, PMP, ENV SP
AIH President, 2021-2022

Congratulations to New Members

Congratulations to those who have been recently certified as Professional members of the American Institute of Hydrology!

Matthew Burnette – PH Surface Water

David Ho – PH Surface Water

Bill Szafranski – PH Surface Water

Megan Gehrke – PH Water Quality

Ji Qi – PH Surface Water

Vignon Houenou – PH Surface Water

Justin Coffman – PH Surface Water

Andrew Earles – PH Surface Water

Robert Parrish – PH Surface Water

Sarah Harris – PH Surface Water

Sean Aucion – Hydrologic Technician I

Nikolaos Apsilidis – PH Surface Water

John Ramirez-Avila – PH Surface Water 

Call for Photos

Our industry-diverse membership often finds themselves in a variety of interesting locations either performing research, working on a project, or attending a conference. And, with some of us now working from home our additional ‘hydro-office’ serves as another “interesting” location to add to the collection.

We want to broadcast the diversity of the hydrology industry and specifically showcase our AIH certified members. Take a moment to snap a few photos of your surroundings so we can paint a clearer picture of what hydrology really looks like. Are your cats or family part of your work from home life? Include them! Do you spend time surrounded by nature and breathtaking environments? We want to see it all!

Upload your photos to this link [https://www.dropbox.com/request/jLQB3udMBGFaAJLw0LEB] and label the file with your name, the location, and your agency.

Thank you for assisting us as we enhance and strengthen the standing of hydrology as a science and profession.

AIH Meet & Greet Event

AIH is planning a Meet and Greet interactive virtual event on September 9, 2021 from 3:00 to 4:00 PM (PDT). The event is designed for AIH’s members to meet and interact with AIH’s Executive Committee, Executive Director, and management office. We will feature opening remarks by AIH President, Jamil Ibrahim, and Executive Director, Sarah Erck, and introductions of AIH’s Executive Committee members. The agenda will also include an overview of AIH’s current initiatives and future activities. We look forward to meeting you and hearing your feedback!

2021 AIH Membership Report

By: Jolyne Lea, Acting Secretary

The 2021 American Institute of Hydrology (AIH) currently has 410 members. An overwhelming majority of the members specialize in surface water hydrology, which is nearly an equal mix of longtime members (who have been certified for over 20 years) and newer members. AIH currently has 15 Hydrologist-in-Training members. There are currently 14 Certified Hydrologic Technician members. Additionally, there are 23 Emeritus members who support the Institute and their profession. Figure 1 shows the Professional, student, and emeritus members by certification identification.

[Figure 1. AIH members by membership category.]

It is also interesting to look at the longevity of our members. The AIH certification identification can be determined when each person was originally certified by AIH. Members range from those who were founding members at the forming of AIH in 1982, to new members. Figure 2 shows current members’ length of membership. There has been a steady influx of new members since 2005, where over ten new members, per year, were certified.

[Figure 2. AIH membership year of certification.]

In figure 3, the membership is grouped in ten-year increments. Over half of the current members (233) have joined within the last twenty years. Long time members of 20-40 years of membership number 151. In the last ten years, AIH has added 112 new members.

[Figure 3. AIH membership grouped by length of membership.]

Lastly, AIH membership is widely distributed across the U.S., Mexico, and Canada. The largest number of members are located in California, Colorado and Texas. In addition, the Institute has ten international members: three from Mexico and seven from Canada.  Figure 4 shows the members by state/country.

[Figure 4. AIH member location]

In summary, based on a review of membership in 2021 compared to historical numbers, the AIH membership numbers appear to be strong and continue to expand with new certified members. The AIH Executive Committee is committed to improving the membership certification process, increasing membership benefits, and expanding student membership to keep the Institute strong for the future. But, we urge our members to contact the AIH Executive Committee regarding input on how AIH membership can continue to be improved and to be active by volunteering for roles where you can.

Interview with Amesha Morris, DEI Committee

Interviewed by: Jule Rizzardo, President-Elect

I sat down with Amesha Morris over a virtual cup of coffee.  Amesha has submitted her application to obtain her Professional Hydrologist certification with AIH, and she serves on the newly formed AIH Diversity, Equity and Inclusion (DEI) Committee. Amesha is currently the stormwater program manager for the City of McKinney’s Stormwater Management Program in North Central Texas.

What is the most challenging thing about your job?

The most challenging part of my job is communication. My work requires coordination with 10 different departments and every year our permit has new requirements. It can be hard to juggle communicating with multiple personnel about changing parameters and changing program requirements.

Describe the most fun project team you’ve been part of at work?

Our department has been upgrading our data to be visualized using GIS. I have been nerding out, because we now have so many more options to display and analyze stormwater data.

What’s something people would be surprised to find out about you outside of work?

I started watching kdramas while I was in graduate school.  It was the perfect way to forget about my thesis for a few hours.

What is one thing you’re glad you tried but would never do again?

The Portland Saint Patty’s Fest Celebration – the event started with running a marathon and ended with lots of singing, dancing, and people celebrating in green.

What’s your favorite hydrologic feature and why?

Honestly, I enjoy a well-designed bioswale with diverse landscaping. Working in stormwater, I’ve learned that green infrastructure can be functional and aesthetically pleasing.

What is the best vacation you’ve taken?

I’m currently on a getaway vacation in Paso Robles California with my best friends, but the best vacation I’ve ever taken was visiting my dad stationed in Korea.

Where in the world do you want to travel next?

I really want to go to Portugal!  It seems like the perfect blend of metro and nature. If I could, I would love to retire there when the time comes.

Hydrologic Impacts of Water Resources Development

(a review of commonly overlooked hydrologic impacts)

By: Anand Prakash, Ph.D., P.E., P.H., F.ASCE, FIE

Capital and operation costs and the ensuing benefits are by far the most dominant determinant for the viability of any water resources development project. However, a cursory review of the analyses of a few recently completed projects indicates that some, relatively obscure, quantifiable and non-quantifiable hydrologic impacts and associated environmental costs are not adequately accounted for in the decision-making process. Examples of such implicit, though inherent, hydrologic impacts are identified herein. 

Quantifiable Perpetual Watershed Management – Perpetual floodplain management is necessitated due to continuing long-term alterations of the floodplain and potential future (almost permanent) damage to the hydrologic environment attributable to the project. A simple approach for continuing watershed management is to ensure that a constant amount of annual floodplain management fund, R1, is available in perpetuity. This amount has to be estimated by the project team based on judgment and experience. With an annual discount rate, i, the capitalized value over the project life, N, is given by, C1 = R1 [{(1+i) N – 1}/{ i (1+i)N }]. For perpetuity, with a large value of N, this gives C1 ≈ [ R1 / i ].      

Quantifiable Infrequent Flood Damages – These are damages due to flood events exceeding the design basis, which may occur during the project life. This cost may not be explicitly specified in project estimates, but has to be incurred periodically as special repairs. Quantification of such damages includes hydrologic modeling and economic analysis to develop a table of flood exceedance probability, Pk, versus damage, Dk, for selected return periods, k, above the design basis flood, arranged in descending order of Pk; and computation of incremental probability, ΔPk = (Pk – Pk+1); and the corresponding average damage, Davk = [(Dk + Dk+1)/2]. The expected annual damage, R2, is estimated as R2 = ∑ (Davk ΔPk) = ∫ Dk dPk and capitalized over the project life as C2 = R2 [{(1+i)N – 1}/{ i (1+i)N }].  The summation or integral goes from a low value of Pk indicative of catastrophic damages to a threshold (high) value of Pk, above which flood damages are considered insignificant. The lower limit may correspond to the design basis flood for the project. 

Quantifiable Consequences of Hydrologic Failure – A scary psychological concern related to major hydraulic structures, particularly dams, is that a major component may fail during the hydrologic event of probability, P, which exceeds the design basis flood. It may be worthwhile to consider insurance, indemnification, or some other compensation for such a hydrologic failure. Even though failure may or may not occur during the project life, the scare, though intangible, can result in real and involuntary hydrologic damage, and its causation is the project. Conceptually, the hydrologist, with the help of an economist, may estimate the present value, V, of failure consequences due to a flood of probability P. Statistically, the probability of failure in the nth year with no failure up to year n-1, is Pn = P (1-P) (n-1). So, expected present value of failure in the nth year = V P [(1-P) (n-1)] and expected insurance cost, C3, for N years of project life is, ∑ V P[(1-P) (n-1)]; the summation is from n = 1 to N. This gives, C3 = V{1-(1-P) N}.                                                                              

Non-Quantifiable Impacts – In addition to quantifiable impacts, there are hydrologic impacts which are not amenable to numeric quantification. Qualitative assessment of such impacts would require detailed hydrologic modeling for the affected surface and groundwater environment. One example of such impacts includes resettlement for which the hydrologist delineates the zone of evacuation to accommodate project structures. The compensation for evacuees must include a one-time payment to legal landowners and social cost for resettlement, rehabilitation, and development of the displaced population to an equivalent or better living standard. This must also include remedial or compensatory measures for the loss or dislocation of wildlife, fisheries, aquatic biota, forests, vegetation, unique historic features, and threatened or endangered plant and animal habitat. Other examples include project impacts on the floodplains and water quality including enhanced waterlogging potential downstream and safe decommissioning of project features at the end of the project life to ensure minimal impacts on future hydrologic environment. Despite being intractable in terms of present value, these impacts must be included in project costs.

Prudent decision making requires that due weight be given to all conceivable tangible and intangible hydrologic and environmental impacts, benefits, and leverage, and a consensus-based iterative process be used to finalize project planning in preference to the commonly used benefit-cost ratio based solely on quantifiable investments and revenues.

About Author

The author is a water resources engineer and has been working in the field for over sixty years. His professional activities include hydrologic and hydraulic analyses involving surface and groundwater flows, contaminant transport and designs of hydraulic structures (dams, spillways, tailings dams, riverine structures, groundwater pumping and dewatering wells, etc.) related to about 200 projects worldwide.

The Rise of Machine Learning in Hydrology and Other Natural Sciences

By: Xiang Li, Ankush Khandelwal, Christopher Duffy, Vipin Kumar , John L. Nieber, and Michael Steinbach

In 2016 AlphaGo and its successor programs defeated human Go professionals using AI (artificial intelligence) (AlphaGo, n.d.). AlphaGo was developed to test how well a neural network using deep learning can compete at the game Go and other board games (chess) without being taught the rules.  The tremendous growth in “AI,” “machine learning (ML),” and “big data” has declared a new era sometimes called the “fourth industrial revolution,” which has fundamentally changed the way we live and work. For example, customers are targeted with more effective business advertisements. Live captions on the media are more semantically accurate. Behind these scenes is the advent of machine learning.   

Although the unreasonably effective predictive performance of ML models may make them appear mysterious to some (Sejnowski, 2020), they are not unintelligible to practitioners. In simplest terms, any applicable ML model can be broken down into three components: general model architecture, purpose-orientated loss function, and an optimization algorithm. (Technically, linear regression is also an ML model.) These components can be customized and re-designed for a specific problem. With appropriate modification, an ML algorithm can be transformed to solve a well-defined problem even for specialized science and engineering domains with data-rich scenarios. This generalizability is a blueprint for ML applications. 

Indeed, in the natural sciences, ML is already having an enormous impact, e.g., ML was relevant to thirteen percent of all STEM papers submitted in 2019 (ArXiv Submission Rate Statistics, 2020). The increasing availability of large volumes of scientific data provides unprecedented opportunities for data-centric research. While ML can discover complex patterns in the data, it is quite distinct from the traditional scientific discovery paradigm. Both ML and knowledge-based discovery aim to determine a logical path connecting data to a conclusion. The data-driven pathway may not follow scientific guidelines and usually ignores the wealth of accumulated scientific knowledge. On the other hand, the knowledge-based pathway does not fully leverage the information hidden in data since the scientific processes involved might not comprehensively explain all interesting patterns in data. To bridge this gap between ML and knowledge-based discovery, there is an emerging research direction named “Knowledge Guided Machine Learning” (KGML) that has captured the interest of both academia and industry. In a nutshell, the information behind the data can be transformed into knowledge. With the guidance of scientific knowledge from domain experts, the KGML framework accelerates science discovery processes. 

In August 2020, the University of Minnesota Twin Cities held an inaugural 3-day virtual workshop, which engaged worldwide researchers to discuss the KGML framework (1st Workshop on Knowledge Guided Machine Learning (KGML), 2020; 2nd Workshop on Knowledge Guided Machine Learning (KGML), 2021), which engaged researchers worldwide for discussions on the KGML framework. Among the natural science sessions covered in the workshop, one session involved the domain of hydrology. In that session, one of the delivered presentations was how to use KGML to predict basin discharge by incorporating hydrologic knowledge into an ML model. This implementation demonstrated some success at emulating the streamflow mechanism of the well-known hydrologic model, SWAT (Khandelwal et al., 2020). In one small watershed in Southeast Minnesota, the SWAT generated discharge was emulated satisfactorily when the ML model adopted concepts of hydrologic system memories, such as soil moisture and snow accumulation. As shown in Figure 1 (1-year data for visualization), KGML improves streamflow prediction compared to the case when no physics is included in the ML model. Putting those time series data in a scatter plot, it clearly shows that KGML prediction matches with the SWAT synthetic data more consistently. Through the whole testing period, the NSE score improves from 0.57 to 0.76 when implementing KGML. 

Figure 1. Emulation of the SWAT model in the South Branch of the Root River at Garden Meadow in SE MN. KGML (blue solid line) improves the pure ML model (orange dashed line) performance. Note that ‘observation’ is the SWAT synthetic data.

Although still at an early stage, both ML and KGML exhibit their remarkable potential in hydrology. Scientific discovery and the understanding of complex hydrologic systems awaits help from these epoch-making data-driven methods. Considering that the future is bright for data acquisition, especially with the ever-increasing amount of satellite data and inexpensive ground-based data acquisition systems, this bodes well for future applications of ML coupled with physics models. In addition to this result at the KGML2020, broad application successes of ML across domains were also discussed at the workshop, including applications in weather forecasting, lake modeling, and cancer diagnosis. This leads to the question: “When so many disciplines embrace the rise of ML, how should hydrologists adapt to this burgeoning trend in such a short time? ” 

The International Association of Scientific Hydrology (IAHS) proposed the dedication in 2003-2012 to “Prediction in Ungauged Basin” (PUB) (Sivapalan et al., 2003). Following that theme, in the next decade (2013-2022), the theme became “Prediction Under Change” (PUC) (Sivapalan, 2011). One traditional approach to modeling hydrologic systems is the physically-based hydrologic model, which predicts watershed responses by lumping hydrological processes into the catchment system. However, the performance of such models is not satisfactory in all basins. As a result, there has been an increasing trend to take advantage of the predictive power of ML in hydrology. ML models outperform physically-based models in some instances, but it should be noted that pure ML models will definitely not replace hydrological models because they rely heavily on data richness. ML is unsuited for the data insufficient basins situation. However, it would make sense to utilize the forecast ability of ML to solve hydrology problems by incorporating principles of hydrology (e.g., conservation of mass, conservation of energy, etc.). Consequently, KGML will be an appropriate candidate approach that implements ML under the guidance of hydrology knowledge, which requires significant collaborative research efforts between data scientists and hydrologists. Coupling physically-based hydrological models and data-driven ML models will be a future research direction for comprehending complicated watershed systems. While interdisciplinary research efforts are continually contributing to model complex hydrological systems with the assistance from ML, it is anticipated that more definitive answers to the PUB and PUC themes will gradually develop within this decade. 

References: 

1st Workshop on Knowledge Guided Machine Learning (KGML). (2020). University of Minnesota. https://sites.google.com/umn.edu/kgml/

2nd Workshop on Knowledge Guided Machine Learning (KGML). (2021). University of Minnesota. https://sites.google.com/umn.edu/kgmlworkshop/workshop 

AlphaGo. (n.d.). Wikipedia. Retrieved June 28, 2021, from https://en.wikipedia.org/wiki/AlphaGo

arXiv submission rate statistics. (2020). Cornell University. https://arxiv.org/help/stats/2019_by_area

Khandelwal, A., Xu, S., Li, X., Jia, X., Stienbach, M., Duffy, C., Nieber, J., & Kumar, V. (2020). Physics Guided Machine Learning Methods for Hydrology. AAAI Symposium.

Sejnowski, T. J. (2020). The unreasonable effectiveness of deep learning in artificial intelligence. Proceedings of the National Academy of Sciences of the United States of America, 117(48), 30033–30038. https://doi.org/10.1073/pnas.1907373117

Sivapalan, M. (2011). Prediction under change (PUC): Water, Earth and Biota in the Anthropocene. AGU Fall Meeting Abstracts, April, 1–64. http://adsabs.harvard.edu/abs/2011AGUFMGC34B..01S

Sivapalan, M., Takeuchi, K., Franks, S. W., Gupta, V. K., Karambiri, H., Lakshmi, V., Liang, X., McDonnell, J. J., Mendiondo, E. M., O’Connell, P. E., Oki, T., Pomeroy, J. W., Schertzer, D., Uhlenbrook, S., & Zehe, E. (2003). IAHS Decade on Predictions in Ungauged Basins (PUB), 2003-2012: Shaping an exciting future for the hydrological sciences. Hydrological Sciences Journal, 48(6), 857–880. https://doi.org/10.1623/hysj.48.6.857.51421

About Authors

Xiang Li is a current PhD candidate in the Water Resources Science program at the University of Minnesota. He has declared a graduate minor in computer science (machine learning and data mining in particular) at UMN. His master thesis is about baseflow recession analysis and groundwater storage change analysis. His current work focuses on integrating machine learning algorithms into hydrology modeling, including SWAT models and classic baseflow recession analysis.

Ankush Khandelwal is a Research Associate in the Computer Science Department at University of Minnesota. He has a PhD in Computer Science from University of Minnesota. Khandelwal’s research has been focused on developing novel machine learning algorithms to analyze vast amounts of satellite imagery for different earth science domains such as water, agriculture and forestry. His current research work is focused on developing physics aware machine learning algorithms for hydrological applications.

John L. Nieber is a native of Upstate New York and he received his B.S. degree in Forest Engineering at Syracuse University in 1972, his M.S. degree in Civil and Environmental Engineering at Cornell University in 1974, and his Ph.D. in Agricultural Engineering at Cornell University in 1979. He is the Full Professor at the University of Minnesota in the Bioproducts and Biosystems Engineering department. John’s research interests involve hydrologic process discovery and modeling, with particular interest in flow and transport processes in porous media. Current research involves studies on utilizing infiltration for stormwater control in urban areas, assessing best management practices impacts on reduction of nitrate in groundwater, combining hydrologic models with machine learning, and quantifying mass and energy transport processes in urban ecosystems.

Christopher Duffy is an Emeritus Professor in the Civil and Environmental Engineering Department of Penn State University. He has held appointments at Los Alamos National lab (1998-99), Cornell University (1987-88), Ecole Polytechnic Lausanne (2006-07), Smithsonian Institution, University Bristol, UK (2014-2016) University of Bonn, DE (2015). Duffy and his team focus on developing spatially-distributed, physics-based computational models for multi-scale, multi-process water resources applications (http://www.pihm.psu.edu/), supported by automated data services (www.hydroterre.psu.edu). Recent research as PI/Co-PI includes: NSF Critical Zone Observatory, NSF INSPIRE, NSF EarthCube, EPA, CNH, DARPA World Modelers and NSF HDR.

Vipin Kumar is a Regents Professor at the University of Minnesota, where he holds the William Norris Endowed Chair in the Department of Computer Science and Engineering. He has authored over 400 research articles, and has coedited or coauthored 10 books including two textbooks “Introduction to Parallel Computing” and “Introduction to Data Mining”, that are used world-wide and have been translated into many languages. Kumar’s current major research focus is on bringing the power of big data and machine learning to understand the impact of human induced changes on the Earth and its environment. Kumar has been elected a Fellow of the American Association for Advancement for Science (AAAS), Association for Computing Machinery (ACM), Institute of Electrical and Electronics Engineers (IEEE), and Society for Industrial and Applied Mathematics (SIAM). Kumar’s foundational research in data mining and high-performance computing has been honored by the ACM SIGKDD 2012 Innovation Award, which is the highest award for technical excellence in the field of Knowledge Discovery and Data Mining (KDD), and the 2016 IEEE Computer Society Sidney Fernbach Award, one of IEEE Computer Society’s highest awards in high-performance computing.

Michael Steinbach earned his B.S. degree in Mathematics, a M.S. degree in Statistics, and M.S. and Ph.D. degrees in Computer Science from the University of Minnesota. He is currently a researcher in the Department of Computer Science and Engineering at the University of Minnesota, Twin Cities working in the research group of Prof. Vipin Kumar.  His research interests are in the area of data mining, machine learning, biomedical informatics, and statistics.  Dr. Steinbach is a co-author of the data mining textbook, Introduction to Data Mining, published by Addison-Wesley, which is used world-wide and has been translated into many languages. Previously, he held a variety of software engineering, analysis, and design positions in industry at Silicon Biology, Racotek, and NCR.