CSDMS - User contributions [en]

2026 CSDMS meeting-030

2026-04-06T19:46:26Z

Jrymart:

{{CSDMS meeting personal information template-2026
|CSDMS meeting first name=Jo
|CSDMS meeting last name=Martin
|CSDMS meeting institute=University of Colorado, Boulder
|CSDMS meeting city=Boulder
|CSDMS meeting country=United States
|CSDMS meeting state=Colorado
|CSDMS meeting email address=jo.martin@moosecow.net
}}
{{CSDMS meeting select clinics1 2026
|CSDMS_meeting_select_clinics1_2026=3) Advancing Spatiotemporal Modeling with Deep Learning: CNN-LSTM Integration
}}
{{CSDMS meeting select clinics2 2026
|CSDMS_meeting_select_clinics2_2026=3) Using Machine Learning for Landscape Feature Detection: Beaver Dams and Beyond!
}}
{{CSDMS meeting select clinics3 2026
|CSDMS_meeting_select_clinics3_2026=1) TopoRivBlender: Reproducible 3D Visualizations in Blender and Python
}}
{{CSDMS meeting abstract yes no 2026
|CSDMS meeting abstract submit 2026=Yes
}}
{{CSDMS meeting abstract poster Epub 2026
|CSDMS meeting poster Epub submit 2026=Poster
}}
{{CSDMS meeting abstract title temp2026
|CSDMS meeting abstract title=Can Neural Networks Think like Geomorphologists?
|Working_group_member_WG_FRG=Terrestrial Working Group
}}
{{CSDMS meeting abstract template 2026
|CSDMS meeting abstract=Neural networks are a machine learning technique that has found massive success across all disciplines, including earth science. So far, their use has primarily been operational: with scientists improving their river forecasts, automating their mapping tasks, and constructing more accurate geophysical inversions. They have shown a great ability to succeed in solving problems in earth science, but they have not yielded an equivalent leap forward in our theoretical understanding of earth systems. While neural networks are often discussed as “black boxes” this is not inherently the case; they can be interrogated and the patterns they have learned can be understood through the lens of our existing physical theory.

Water leaves a fingerprint on landscapes, but we still struggle to quantify topography in a way that can be quantitatively related to the surface water hydrology that has shaped it. Convolutional neural networks have an ability to approximate arbitrary spatial functions, and so are an exciting tool to help us quantify topography in geomorphically and hydrologically meaningful ways. In this work we focus on the robustness and scrutability (that is, the ability to understand the internal model of the neural network) of a convolutional neural network trained to infer key geomorphological parameters from modeled topography. Much theoretical geomorphological research has revolved around the idea of landscapes as advective/diffusive systems, and the ways in which the Peclet number of such a system is a key control on its morphology. While topographic data is ample, topographic data that can be labeled with quantitative geomorphic parameters is not, so investigating theoretical models with a neural network both helps us learn how we can interpret neural networks within the context of earth science, and helps us learn more about a widely used theoretical tool. A simple convolutional neural network was trained to extract the Peclet number from the final topography of an advective/diffusive model with a normalized root mean squared error of 0.021.

While this performance shows the ability of neural networks to understand and invert simple theoretical models, “unpacking the black box” and making the model scrutable reveals that it appears to have “learned” some fundamental concepts that match the understanding of geomorphologists. The network demonstrates some understanding of the role of valley spacing as a control of the Peclet number. It demonstrates some understanding of drainage density as being closely tied to the Peclet number. It also demonstrates a preference for topographic derivatives tied to the landscape evolution model chosen, like slope and curvature. While a network trained only on numerical models is not in and of itself useful, this work demonstrates the ways in which neural networks can be successfully probed within the context of geomorphic theory.
}}
{{blank line template}}

2026 CSDMS meeting-030

2026-03-11T16:42:32Z

Jrymart: Created page with "{{CSDMS meeting personal information template-2026 |CSDMS meeting first name=Jo |CSDMS meeting last name=Martin |CSDMS meeting institute=University of Colorado, Boulder |CSDMS meeting city=Boulder |CSDMS meeting country=United States |CSDMS meeting state=Colorado |CSDMS meeting email address=jo.martin@moosecow.net }} {{CSDMS meeting select clinics1 2026 |CSDMS_meeting_select_clinics1_2026=3) Advancing Spatiotemporal Modeling with Deep Learning: CNN-LSTM Integration }} {{..."

File:Jmartin poster vertical 2025.pdf

2025-05-21T17:32:11Z

Jrymart:

2025 CSDMS meeting-069

2025-03-10T20:33:52Z

Jrymart: Created page with "{{CSDMS meeting personal information template-2025 |CSDMS meeting first name=Jo |CSDMS meeting last name=Martin |CSDMS meeting institute=CU Boulder |CSDMS meeting city=Boulder |CSDMS meeting country=United States |CSDMS meeting state=Colorado |CSDMS meeting email address=jo.martin@colorado.edu |CSDMS meeting phone=7733444470 }} {{CSDMS meeting select clinics1 2025 |CSDMS_meeting_select_clinics1_2025=1) Coupled Simulations in ASPECT/FastScape Part 1 }} {{CSDMS meeting sel..."

{{CSDMS meeting personal information template-2025
|CSDMS meeting first name=Jo
|CSDMS meeting last name=Martin
|CSDMS meeting institute=CU Boulder
|CSDMS meeting city=Boulder
|CSDMS meeting country=United States
|CSDMS meeting state=Colorado
|CSDMS meeting email address=jo.martin@colorado.edu
|CSDMS meeting phone=7733444470
}}
{{CSDMS meeting select clinics1 2025
|CSDMS_meeting_select_clinics1_2025=1) Coupled Simulations in ASPECT/FastScape Part 1
}}
{{CSDMS meeting select clinics2 2025
|CSDMS_meeting_select_clinics2_2025=1) Coupled Simulations in ASPECT/FastScape Part 2
}}
{{CSDMS meeting select clinics3 2025
|CSDMS_meeting_select_clinics3_2025=3) Using the Collaborative Sandpiper Toolchain to Support Interoperability in Geomorphology Research
}}
{{CSDMS meeting abstract yes no 2025
|CSDMS meeting abstract submit 2025=Yes
}}
{{CSDMS meeting abstract poster Epub 2025
|CSDMS meeting poster Epub submit 2025=Poster
}}
{{CSDMS meeting abstract title temp2025
|CSDMS meeting abstract title=Neural Networks Can Infer Geomorphic Model Parameters From Topography, and We Might Be Able To Figure Out How!
|Working_group_member_WG_FRG=Terrestrial Working Group
}}
{{CSDMS meeting abstract template 2025
|CSDMS meeting abstract=From the classic U-shaped glacial valley to the convex soil-mantled hillslope, geomorphic processes leave clear signatures on the landscapes they create. However, it has been challenging to develop topographic metrics that can be used to extract process parameters. While researchers have gained significant insights into geomorphic processes through metrics like mean local relief, channel steepness, and ridgetop curvature, it is still difficult to make quantitative predictions about processes from quantitative topographic measurements.

Prior modeling work has found that in 2D models that combine stream incision with diffusive hillslope processes, valley spacing is strongly controlled by the relative rates of advective and diffusive processes (Perron et al. 2008). In this work we train a simple convolutional neural network to predict the ratio of the coefficient of stream erosion (K) and coefficient of diffusion (D) used to generate the model topography. Across a test set of 1800 model runs with different K and D values, the network had a normalized root mean square error of 0.03, showing that convolutional neural networks have significant promise for extracting complex and geomorphically meaningful topographic signatures.

In this work we focus on interpreting the neural network to try to help explain what it is calculating in a theoretically grounded way. The output of activation maximization, Fourier analysis, neuron ablation, and other interpretability techniques are complicated, but might imply that the network is detecting patterns that are geographically meaningful. This poster will present these interpretability results.
}}
{{blank line template}}

User:Jrymart

2024-05-15T15:16:12Z

Jrymart:

{{Signup information member
|First name member=Jo
|Last name member=Martin
|Pronouns=she/her/hers
|Institute member=University of Colorado Boulder
|Department member=Geology
|City member=Boulder
|Country member=United States
|State member=Colorado
|Confirm email member=jo.martin@colorado.edu
|Working group member=Terrestrial Working Group, Education and Knowledge Transfer (EKT) Working Group, Hydrology Focus Research Group, Artificial Intelligence & Machine Learning Initiative, River Network Modeling Initiative
|Emaillist group member=yes
|Description of your CSDMS-related interests member=rivers, math, graph theory
|Memberagreement=I have read and agree to the Privacy Policy
}}

2024 CSDMS meeting-078

2024-03-18T18:29:22Z

Jrymart:

2024 CSDMS meeting-078

2024-03-18T18:27:53Z

Jrymart: Created page with "{{CSDMS meeting personal information template-2024 |CSDMS meeting first name=Jo |CSDMS meeting last name=Martin |CSDMS meeting institute=CU Boulder |CSDMS meeting city=Boulder |CSDMS meeting country=United States |CSDMS meeting state=Colorado |CSDMS meeting email address=jo.martin@colorado.edu |CSDMS meeting phone=773 344-4470 }} {{CSDMS meeting select clinics1 2024 |CSDMS_meeting_select_clinics1_2024=3) Introduction to agent-based modeling for socio-environmental system..."

{{CSDMS meeting personal information template-2024
|CSDMS meeting first name=Jo
|CSDMS meeting last name=Martin
|CSDMS meeting institute=CU Boulder
|CSDMS meeting city=Boulder
|CSDMS meeting country=United States
|CSDMS meeting state=Colorado
|CSDMS meeting email address=jo.martin@colorado.edu
|CSDMS meeting phone=773 344-4470
}}
{{CSDMS meeting select clinics1 2024
|CSDMS_meeting_select_clinics1_2024=3) Introduction to agent-based modeling for socio-environmental systems
}}
{{CSDMS meeting select clinics2 2024
|CSDMS_meeting_select_clinics2_2024=2) Introduction & Building with Google Earth Engine: Batteries Included
}}
{{CSDMS meeting select clinics3 2024
|CSDMS_meeting_select_clinics3_2024=4) A Hands-On Workshop on GPU-Based Landscape Evolution Modeling
}}
{{CSDMS meeting abstract yes no 2024
|CSDMS meeting abstract submit 2024=Yes
}}
{{CSDMS meeting abstract poster Epub 2024
|CSDMS meeting poster Epub submit 2024=Poster
}}
{{CSDMS meeting abstract title temp2024
|CSDMS meeting abstract title=Please be seated.
First on behalf of Lou and Brian, let me welcome you to Philadelphia (go birds) and thank you all for traveling to the beautiful Francie Cope House. If you live in Philadelphia understand that your thanks is reasonably somewhat muted, as we are not more than a thousand feet from a regional rail station. For those of you traveling from far away, say from about Colorado or farther, you get the extra thanks we took from the Philadelphians.

My name is Jo, and I became friends with Tyler and Annie shortly before I moved to Philadelphia in 2020. After I ended up just a few blocks away from them, they quickly became two of my closest friends, and probably the people I saw in Philadelphia the most frequently. I showed them movies that Tyler loved and Annie hated. I unsuccessfully helped Annie try to bully Tyler into climbing. And joined both of them in their favorite pastime, staring adoringly at Lou. This friendship peaked when they asked me to officiate their wedding in the philadelphia hard rock cafe in what ended up as a surprisingly macabre scene. It goes without saying how honored I am to be here with them, in front of their family and their friends and assist them in this wedding.

We are here today to celebrate the love of Annie and Tyler, and to witness and take part in their continued commitment to each other. Annie and Tyler met in June of 2017 in San Juan National Forest. They met as friends of friends, Tyler going on a yearly trip with his childhood friends, and Annie diving into the unknown, backpacking for the first time with her college friends from Saint Louis. They quickly found they shared a sense of humor and mutual appetite for time together, often ditching the friends they had come there to be with and hiking side by side behind the rest of the group. The affection they had for each other was clear, and when Anie left a jacket with the group before her flight, Tyler was immediately and unanimously chosen to return it to her, preferably in person.

After returning to their respective homes, they texted frequently, sharing jokes, movie reviews, and mundane details about their days. They texted so frequently in fact that Annie spent her last bad date texting Tyler the whole play by play as it happened. After that, it was clear that this was a relationship that needed to be pursued despite the distance. And so for the next two years Tyler visits DC, Annie visits saint louis and the relationship begins to blossom. Then Annie makes the somewhat explicable decision to move to Chicago for what they called “medium distance”.

Despite the distance their relationship continued to flourish thanks to nonstop texting, frequent facetime, long distance movie dates, plane tickets, train tickets, and of course more backing trips with that same beloved group of friends that brought them together in the first place. And finally, in 2019 they both move to Philadelphia, together for the same time as a couple for the first time.
When I asked them what they liked about each other, what drew them towards each other, and the commitment of marriage, initially they were both unhelpful. This was, I do not think, due to the inherently malicious nature of either Tyler or Annie. Instead, it speaks to how completely they see everything they could want in a partner. Humor, intelligence, compassion, looks; they do not find each other lacking. Both this mutual love and the strong character that you both possess and see in each other is evident to all those who are close to you.

Annie, you said that you were drawn to Tyler’s grace and quiet charisma and through his actions and being, you have been taught patience and kindness. You said that Tyler is everyone's favorite person, which isn’t wrong, so be proud that you are marrying him.

Tyler, in Annie you found someone caring and confident, who pushed you out of your comfort zone and helped you build a dynamic and fulfilling life. You told me that Annie is someone who cares deeply about the people in her life and loves to make them happy, so be proud that you are marrying her.

May you continue to have a life where you share not only love and humor, but continued growth at the hand of the other.

One thing you both said to me was how much you admired the other's ability to make friends. These friendships are the reason you found each other. The friendships you’ve made since then would not be possible without the other, and these friends both old and new are represented here today.

Now two of these friends will give readings on love, picked by the couple.

Tyler and Annie, your marriage is a celebration that you both have been lucky to meet each other, and admire and respect each other; trust each other, and most importantly love each other so much. You understand the unique value of commitment and choose to undergo the personal bond of marriage to remind yourselves that you are on a long journey to build something stronger, and bigger than either of you individually; something that you could not do on your own. You undergo this deep legal commitment because you understand how deeply you want your lives to be interconnected, pooling resources to build a home together and to be responsible for not only each other's happiness but each other's livelihood.

But this commitment is also not only personally meaningful to you, it's practically meaningful to your community gathered here today. Annie, at your bachelorette party I met Carly, someone Tyler has known for his entire life, and Tyler, at your bachelor party, was Jordan, one of Annie’s closest college friends, and Brannon, the husband of another! Not only have you brought your friends into each other's lives, but you have made new friends together, and brought those friends together with each other forming new friendships, new friendships that will form and deepen even today. By committing to each other so fully, you cement the many friendships you have brought together over these past 5 years making it clear that your commitment to each other is also a commitment to these many relationships you have fostered.

Annie and Tyler, not only have you built the many friendships that you see here today, you were also brought together by your friendships and so your love is, among many things, a testament to your many wonderful friends. And just as you both have built and relied on many strong friendships, I have no doubt that you will build an equally strong marriage.

Tyler and Annie are self uniting, as is their right in the great commonwealth of Pennsylvania. However, to honor their commitment in front of their family and friends, I ask them:

Tyler, do you vow to continue to build your life together, with sweetness and love, to help each other grow, to keep the spirit of rock and roll alive, and and to care for each other like you have both cared for all of the people here who serve as witness?

Annie, do you vow to continue to build your life together, with sweetness and love, to help each other grow, to keep the spirit of rock and roll alive, and and to care for each other like you have both cared for all of the people here who serve as witness?

<You say I do and shit>

Then take these rings, and may they serve as a reminder of your commitment to each other and a symbol of your love.

By the highest powers we know, Lou and Brian, I pronounce you married.

Fractal Dimensions of River Networks and Hack's Law
|Working_group_member_WG_FRG=Hydrology Focus Research Group
}}
{{CSDMS meeting abstract template 2024
|CSDMS meeting abstract=Fractal geometry is a branch of mathematics pioneered by Benoit Mandelbrot in the 1970's with the goal of finding a mathematically rigorous way to define the geometry found in nature, including what he saw in river networks. Since then, much work on the geometry and structure of river networks has involved fractal method, from passing mention to assumed fractal characteristic's to trying to tie older geomorphic parameters to Mandelbrot's fractal math. However results on the fractal dimensions of river networks have been contradictory and not always well matched to theoretical explanations of fractal geometry. For example, in a 1988 work, Tarboton et al. found that the measured fractal dimension of river networks transitioned from close to 1 at small scales to close to 2 at large scales. They attributed this to switching from a regime where fractal dimension was dominated by Sinuosity to one where it was dominated by the branching characteristics of rivers. Neither of these matches Mandelbrot's prediction of a fractal dimension of 1.2 for river networks, which he derived from a Hack exponent of 0.6, used in the relation between stream length and basin area, which would likely be influenced by river branching. More recent unpublished calculation of the fractal dimension of large North American river basins found a dimension close 1.1, which conveniently would correspond to a Hack exponent of 0.55 which matches more recent empirical work on Hack's law. To better understand the connection between fractal dimension and Hack's Law, in this poster I present work comparing the fractal dimension of modeled river networks to physical ones, and look at what theoretical parameters may explain them variability in measured fractal dimensions of river networks.
}}
{{blank line template}}

User:Jrymart

2023-12-04T19:35:41Z

Jrymart: Created page with "{{Signup information member |First name member=Jo |Last name member=Martin |Pronouns=she/her/hers |Institute member=University of Colorado Boulder |Department member=Geology |City member=Boulder |Country member=United States |State member=Colorado |Confirm email member=jo.martin@colorado.edu |Working group member=Education and Knowledge Transfer (EKT) Working Group, Cyberinformatics and Numerics Working Group, Hydrology Focus Research Group, Artificial Intelligence & Mac..."

{{Signup information member
|First name member=Jo
|Last name member=Martin
|Pronouns=she/her/hers
|Institute member=University of Colorado Boulder
|Department member=Geology
|City member=Boulder
|Country member=United States
|State member=Colorado
|Confirm email member=jo.martin@colorado.edu
|Working group member=Education and Knowledge Transfer (EKT) Working Group, Cyberinformatics and Numerics Working Group, Hydrology Focus Research Group, Artificial Intelligence & Machine Learning Initiative, River Network Modeling Initiative
|Emaillist group member=yes
|Description of your CSDMS-related interests member=rivers, math, graph theory
|Memberagreement=I have read and agree to the Privacy Policy
}}