Thursday, June 22, 2023

A Ph.D. position on Po River, DARTHs, Earth Observations

I have an open Ph.D. position which closes at July 6: - Evolution of the system GEOframe/OMS3/CSIP for the building ofa Digital Twin of the Hydrology of river Po - E66E23000170001 

It looks like it is very dedicate to informatics (see also here) but let me say that the candidate should write their  project with a broader view, although it must remain within the scope of what we are doing in the context of the Po River basin project and  related to the exploitation of satellite data to support hydrological modeling. The project that funds it, besides PNRR,  is 4DHYdro, which collects some of the best hydrological modellers in Europe (and from the projects' goal you can find inspiration). 

The general focus of the study are droughts and can contains more computer science-related parts, more conceptual parts, or more applied parts. The themes related to the processes are: snow, plant transpiration, and crop needs. The enabling technology is precisely the systematic use of Earth observation, and the concept paper for the whole system is the one about DARTHs. Further information on DARTHs can be found here

If, at this point, you are a little convinced to apply also consider the philosophy of our group that you can find in a sequence of posts, here and and links therein.

Our group is a  crew of international fellows: 2 Indians, 1 Pakistani, 1French, 1 Iranian, 1 Algerian and 8 Italians, including two professors, one researcher (at Eurac), two postdocs, and nine Ph.D. students already. 

Saturday, June 10, 2023

Transit time, Residence time, Response time, Life expectancy

 Just to help someone, a few definitions:

  • Travel Time (a.k.a. Transit Time), T: It is the time a parcel of water stays inside a control volume. If $t_{in}$ is the time it entered the control volume and $$t_{ex}$$ the travel time it exits, then $$ T= t_{ex}-t_{in} $$ For an observer placed at the outlet(s) of the control volume, since their actual (clock) time coincides with $$t_{ex}$$, i.e $$t_{ex}=t$$ it is $$ T= t-t_{in} $$. The actual variable in this definition is $$t_{in}$$

  • Residence time is $$T_R = t-t_{in}$$
  • Life expectancy is $$ T_L = T_{ex} - t$$ so, it is also: $$ T = T_R+T_L $$ 
  • Response time is $$R = t_{ex}-t_{in}$$ but only restricted to all the parcels injected at the same $$t_{in}$$ estimated at $$t=t_{in}$$ and is their life expectancy at  $$t=t_{in}$$. The actual variable here is $$t_{ex}$$.
All of these definitions are given in statistical sense, meaning that they are stochastic variables described trough their distributions. Looking at the above definitions  and if we do not read them very carefully, it looks like that transit time and response time are the same thing and we though for decades it was. Instead they are not since transit time distribution is conditional to the clock time, while response time distribution is conditional to the injection time.  The first is a distribution in $$t_{in}$$, the second in $$t_{ex}$$. 

To learn more, you can get further details at: 

Rigon, Riccardo, Marialaura Bancheri, and Timothy R. Green. 2016. “Age-Ranked Hydrological Budgets and a Travel Time Description of Catchment Hydrology.” Hydrology and Earth System Sciences Discussions, May, 1–22. https://doi.org/10.5194/hess-2016-210. (This paper has a little weird description of life expectancy though)

Rigon, Riccardo, and Marialaura Bancheri. 2021. “On the Relations between the Hydrological Dynamical Systems of Water Budget, Travel Time, Response Time and Tracer Concentrations.” Hydrological Processes 35 (1). https://doi.org/10.1002/hyp.14007. (ad especially give a look to the supplemental material)

See also a concise summary unpublished paper available here

Video lectures in the topic can be found in this blog. The most recent ones are:

Travel Time, Residence Time and Response Time
Here below we started a little series of lectures about a statistical way of seeing water movements in catchments. This view has a long history but recently had a closure with the work of Rinaldo, Botter and coworkers. Here it is presented an alternative vie to their concepts. Some passages could be of some difficulty but the gain in understanding the processes of fluxes formation at catchment scale is, in my view, of great value and deserves some effort.  The way of thinking is the following: a) the overall catchments fluxes are the sum of the movements of many small water volumes (molecules); b) the water of molecules can be seen through 3 distributions: the travel time distribution, the residence time distribution and the response time distributions; c) the relationships between these distributions are revealed; d) the relation of these distributions with the the treatment of the catchments made through ordinary differential equations is obtained through the definition of age ranked distributions; e) The theory this developed is a generalizations of the unit hydrograph theory. 



Monday, May 15, 2023

A talk on how plants eat the Sun

 Tomorrow, for the "23rd International Day of Light" I am giving a talk about how through the photosynthesis plants take water and carbon dioxide to produce oxygen and carbohydrates (lignin and other stuff).  The title was kind of suggested by a book by Oliver Morton of about the same name

Slides and talk are in Italian but I will provide soon an English version of it. By clicking on the figure, please find the presentation pdf. 



Friday, May 12, 2023

Attacking the issue of hydrological scales within GEOframe

 How to face the scale problems in GEOframe. Daniele Andreis is giving his answer by using the capabilities of the GEOframe system.  His approach is simple. Taken a catchment subdividing further the HRUs (with an appropriate software component) in smaller HRUs you are able to run a GEOframe modelling solution to the larger catchment (if required)  with a specific catchment refined and then you can compare the models parameters of the refined solutions with the coarser one. (That's actually not really  done yet ;-)). 

What you see in this poster is the preliminary work where you can notice a couple of nice features: the time series of the monthly, daily and hourly water budget which is unusual to find and the comparison of a neutron probe signal with the simulated root zone water content. The signal are clearly correlated and this can be though as an indirect assessment of the GEOframe modeling solution chosen and let's hope that we can actually calibrate somewhat the root zone parameters with the neutron probe. Clicking on the above figure, please find a larger figure of the poster,  


Monday, April 24, 2023

For inquiring students. - II (and what is ph.D education about)

"My name is John, and I am an M.Sc. student of water engineering at the Beautiful University of Technology. My M.Sc. thesis subject is a groundbreaking one - 'Application of WRF Regional Model for Rainfall Prediction (Case Study: Northwest of Antarctica).' Under the guidance of Prof. Best Hydrologist, I have delved into the impact of predicted precipitation by the WRF model on flood forecasting in the Hec-Hms (or SWAT) model. My expertise and keen interest in climate change impacts on hydroclimatic extremes, numerical weather prediction, hydrology and water resource management, hydraulic and flood forecasting make me a force to be reckoned with in the field. "

I already wrote on the topic of students inquiring about the possibility to do a Ph.D with me. You can find previous notes here. However, I would still add something.

It's heartening to see that many schools are taking the direction of training students to run WRF, Hec-HMS, SWAT, R, Python and other tools. However, mastering tools is just one aspect of research. To truly investigate nature, one must understand where problems are and be able to modify paradigms and tools to solve them appropriately. 

As Richard Feynman said, 'The problem is not people being uneducated. The problem is that people are educated just enough to believe what they have been taught, and not educated enough to question anything from what they have been taught.' 

Becoming a solid Ph.D applicant requires making this switch and adding a few phrases to your  CV that show that you have understood the Feynman's point.  Besides, you should be inquisitive and show some fire inside for discovering new things and achieve results beyond the state-of-art (and for what regards working with me, love computer programming). A PhD is not just a status symbol or a way to gain a good salary - it's a calling for those who are truly passionate about pushing the boundaries of knowledge (see this nice infographics from an old post)

P.S. -  I also wrote this "Essential for Hydrologists" that could further help. 

Tuesday, April 18, 2023

Using ChapGPT 4 for Learning Java

 Currently, there's a lot of hype surrounding ChatGPT v4. I was curious to explore its capabilities, so I used OpenAccessGPT to bypass current Italian law and access the BOT.



I tested ChatGPT v4 by asking it to search for literature on a specific topic - the stomata action under the effect of decreasing tension in xylem. While the results were interesting, they weren't necessarily the best. In fact, when I tested the BOT on more specialized topics, its performance seemed immature.

To improve my experience, I decided to seek help in programming and discovered that ChatGPT v4 could be a valuable resource. I soon realized that my idea wasn't entirely original, as there are many resources available online, such as this YouTube video. Perhaps ChatGPT v4 could have even provided me with this information.

This is what ChapGPT tells on the topic:

"ChatGPT can be a valuable resource for learning Java in several ways:

  1. Asking Questions: You can ask ChatGPT any question you have about Java, such as how to use a specific feature or how to solve a particular problem. ChatGPT can provide you with a detailed explanation or point you in the right direction to find the information you need.
  2. Practice Exercises: ChatGPT can provide you with practice exercises to help you improve your Java skills. These exercises can range from simple coding challenges to more complex projects.
  3. Code Examples: ChatGPT can provide you with Java code examples that illustrate how to use various features and solve different problems. These examples can help you understand Java concepts more easily.
  4. Tutorials and Resources: ChatGPT can recommend Java tutorials and resources that can help you learn more about the language. These resources can include online courses, books, and websites.

Overall, ChatGPT can be a valuable tool for anyone looking to learn Java. It can provide you with personalized assistance, practice exercises, and resources to help you improve your skills and become a proficient Java programmer. "

Browsing the YouTube class, I realized that the approach to Java was good but not the way I desired. So I asked: "Please help me in learning Java but not following the traditional way. I would like that you introduce me early on Java design patterns and topics related to numerical computation. I need also you to introduce me to the use of generics. I would say introduce me to modern Java".  Here below the result

Sure, I can design a ten-hour class on the topics of Java design patterns, numerical computation, and generics. Here's a rough outline:

Day 1 (2 hours):
1. Introduction to Java design patterns
2. Singleton pattern
3. Factory pattern
4. Observer pattern
5. Hands-on exercise

Day 2 (2 hours):
1. Introduction to numerical computation in Java
2. Overview of Apache Commons Math and JScience libraries
3. Basic mathematical operations (addition, subtraction, multiplication, division)
4. Hands-on exercise

Day 3 (2 hours):
1. Statistical analysis using Apache Commons Math
2. Descriptive statistics (mean, median, mode, variance, standard deviation)
3. Hypothesis testing (t-tests, ANOVA)
4. Hands-on exercise

Day 4 (2 hours):
1. Linear algebra using JScience
2. Matrices and vectors
3. Matrix operations (addition, subtraction, multiplication)
4. Eigenvalues and eigenvectors
5. Hands-on exercise

Day 5 (2 hours):
1. Introduction to generics in Java
2. Defining and using generic classes
3. Defining and using generic interfaces
4. Defining and using generic methods
5. Hands-on exercise

Each day will consist of a mixture of lecture-style teaching and hands-on exercises, to ensure that students have a chance to practice what they've learned. The hands-on exercises will involve writing code and solving problems related to the topics covered in class.

By the end of the ten-hour class, students should have a good understanding of Java design patterns, numerical computation, and generics, and be able to apply these concepts to real-world programming problems.

Not sure that I am really satisfied but my further experiments with more detailed questions went better. Therefore, up to a point, the user has also to lear how to interact with the BOT.  When you go on more detailed questions the performance are less generic. For instance, I asked:

Can do you do examples on how define and using generics classes in Java ?

The answer was:

public class Box<T> {
    private T contents;

    public void setContents(T contents) {
        this.contents = contents;
    }

    public T getContents() {
        return contents;
    }
}

This answer is correct by a little obscure to a newbie. So I refined my request: "How can I use the previous class in a main() ?  And I have got:

public class Main {
    public static void main(String[] args) {
        // Create a Box that holds strings
        Box<String> stringBox = new Box<>();

        // Set the contents of the box to a string
        stringBox.setContents("Hello, world!");

        // Get the contents of the box and print it to the console
        String contents = stringBox.getContents();
        System.out.println(contents);
    }
}


with the comment:

"In this example, we create a Box that holds strings using the syntax Box<String>. We then set the contents of the box to the string "Hello, world!" using the setContents method, and retrieve the contents using the getContents method. Finally, we print the contents to the console using System.out.println".

Overall (there were also some other example, this was quite satisfying.  Next step: making ChapGPT learn about our own staff and being able to support, for instance, people in using GEOframe. 

Tuesday, March 21, 2023

2023 Stockholm Water Prize went to Andrea Rinaldo

As any year, the first day of Spring and the day before the Water Day, it is announced the Stockholm Water Prize. The Stockholm Water Prize is often described as the Nobel Prize of water and is characterized by a similar selection process. Since 1991, the Stockholm Water Prize has been awarded to people and organizations for extraordinary water-related achievements. Its official site is SIWI. Last year the Prize was given to Wilfried Brutsaert

This year prize was assigned to Andrea Rinaldo, first Italian to receive it, as a recognition of his achievements and its role for the Italian and International Community of Hydrologist. Professor in Padova and at Ecole Politechnique in Lausanne, he was one of the founder and head of the Civil and Environmental Engineering Department of the University of Trento of the degrees in Environmental Engineering.  The the official announcement has been shared on SIWI’s Youtube channel on Tuesday 21 March, at 3pm CET.  SIWI website (https://siwi.org/stockholm-water-prize/) contains further information. 

Andrea Rinaldo (center) in Mesiano - Trento - Department of Civil, Environment and Mechanical Engineering Department 


Andrea Rinaldo  is one of the most eminent Italian Hydrologists ever. The Italian community of hydrologist bloomed in the last twenty years and is now one of the most active and productive in the World. This was certainly due to the positive action that Andrea Rinaldo started since the late eighties of last century to promote young researchers and put them in contact with some of the most outstanding scientists in the field, starting from Ignacio Rodriguez-Iturbe,  Gedeon Dagan and Peter Eagleson (all of them have received the Stockholm Water Prize),  Raphael Bras and others. He was him between the very few who captured the attention of these greats with his creativity and dedication and involved them in researchers with Italians gifting many youngster of an incomparable education in hydrology. 

He steered the Italian Water Community to put attention on the important topics of water management, hydrology and geomorphology.  Some of the younger Italian scientists could not be aware of that but when some good research is published from Italians, there is a good chance that at least some drops of it have a seed in Rinaldo's academic and scientific work. 


Andrea Rinaldo   himself is an extraordinary researcher. He gave fundamental contributions in understanding the shape of river networks and his book with Ignacio Rodriguez-Iturbe is a long-standing milestone on the subject. The theory of optimal channel networks not only gives explanation of how the river networks evolve and behave but also has risen the interest for hydrology of scientists  working on related disciplines, and, in particular, of those working on transportation networks making hydrology an epitome of many other physical phenomena. 

He contemporarily worked on the theory of the Instantaneous Unit Hydrograph, where his contributions are among the the most cited. More recently he renewed the topic with a couple of papers that completely changed the view on travel times and residence times and related issues. Those contributions are definitive in clarifying the subject and they close with a neat theory ninety years of research history. At the same time those contributions are the seeds of the current studies with tracers and isotopes that are going to push greatly forward our knowledge on water movements in hillslopes and vegetation.


Together with  Rodriguez-Iturbe and younger fellows, he was architect of many eco-hydrological studies since the year 2000 that brought new insights in the soil-vegetation-atmosphere interactions and inspired new directions of research.


While continuing to frequent his vast collections of research topics that he manages masterfully, and where there are many “minor’’ contributions that could just be the reward of a carrier for others, he worked intensively in the last twenty years to understand the mechanics of  the spreading of the water borne diseases and, in general, of the spreading of populations. In this he actually joined together several of his research favorite topics, river networks, water, transportation issues, complexity, theoretical, field and laboratory work. His recent book with Marino Gatto and Ignacio Rodriguez-Iturbe is a compendium of  provoking ideas and methods that certainly will last long in the libraries (virtual or not) of the researchers of the field.