Skip to content
#software testing Open access

SAGEhydrology

Oct 2026 · Zenodo (CERN European Organization for Nuclear Research)
Hydrological Forecasting Using AI

Abstract

SAGEhydrology v1.0.3 This Windows release retains the public capabilities of v1.0.2 and improves standalone deployment, reproducible projects, custom-model loading, and the presentation of training results. It provides seven built-in models and the manual user_model interface. AI-assisted model authoring and private model implementations are excluded. Changes from v1.0.2 Projects: the compiled GUI includes publication Projects 1–5 and the new-user-project workflow. "Open source" opens readable MATLAB exports; scripts for Projects 1–2 are included rather than pointing to missing files. Project settings are locked while a SAGE run is active. Custom C++ models: the manual user_model option is available independently of the AI builder. A sibling user_model folder supplies parameter metadata and a compatible precompiled MEX. Runtime loading no longer calls addpath, and the selected external binary is installed into Runtime's resolved MEX location before evaluation. Users compile replacement C++ models externally, update user_model_info.mat, and restart SAGE before using the replacement. Paths and deployment: Software root can be selected in the executable. Startup recognizes an installation beside Data and SAGEhydrology instead of treating the Runtime cache as the user's software installation. Asset lookup avoids a mandatory call to MATLAB's unavailable internal executable-path API. Installed datasets and maps: Russia/HydroCIS and daily CAMELS-KR checks resolve their bundled basin inventories in Runtime. Existing 10 m map files under SAGEhydrology/maps are detected using the selected software root. The GUI retains the compact 50 m map for responsive interactive rendering. Training preparation and logs: discharge-statistics progress updates are throttled, and model-specific Kosugi requirements are reset when changing models. Detailed log messages use consistent indentation and wrapping. Run summary and controls: model and network parameter counts are shown; the two summary columns have improved spacing, and text/control heights avoid clipped letter descenders. Log buttons use improved vertical spacing. Figures: more consistent ECDF fonts/layouts and tick lengths; shorter hydrograph ticks; readable time-resolution badges; upright variogram panel labels with tighter spacing. Parameter maps are paginated at 20 parameters per figure, with a scale in each figure's top-left panel and its own colorbar. Source examples: exactly three examples are supplied: demo_SAGE.mlx, verify_jacobians_and_gradients.m, and run_SAGE_export_hymod.m. Project 3–5 exports reside in their project folders. Example paths derive the installation root from their file location. Which Windows download should I use? | Download | Purpose | | --- | --- | | SAGE-v1.0.3-Windows-x64-installer.exe | Guided installation; obtains MATLAB Runtime R2026a through web delivery when required. | | SAGE-v1.0.3-Windows-x64-portable.zip | Recommended for an existing Software/Data installation. Includes SAGE.exe, public supporting files, maps, projects, and the manual user-model template/kernel. Requires MATLAB Runtime R2026a. | | SAGE-v1.0.3-Windows-x64.exe | The application executable alone, for replacing an existing installation's executable. Requires MATLAB Runtime R2026a and separately maintained Data/user-model files. | | SAGE-v1.0.3-computational-source.zip | Updated public MATLAB/C++ source and manual user-model template. Requires MATLAB for source execution; contains no GUI source or native binaries. | The installer and portable executable deliver the same v1.0.3 GUI and model capabilities. The difference is installation and Runtime setup, not functionality. Keep SAGE.exe, Data, SAGEhydrology, and user_model beside one another in your Software folder. In Paths, select that Software root and your Data/results locations. Existing datasets do not need to be downloaded again. Run results and large regional datasets are not included in these downloads. Project exports run in MATLAB with the computational source installed; MATLAB Runtime cannot execute arbitrary .m scripts. Compiled GUI use is covered by GUI-LICENSE-NOTICE.md; the public computational source has the BSD 3-Clause License. Readable GUI source, private models, AI-builder files, results, and development caches are excluded from public assets. The accompanying computational-source ZIP is the v1.0.3 source snapshot. Repository files have not been committed as part of this release; GitHub's automatically generated "Source code" archives reflect the existing repository snapshot, so use the explicitly named computational-source asset for these fixes. Platform and validation Windows x64 application and installer packaging passed verification, including nine native MEX inputs. A compiled Runtime test loaded an independently rebuilt external user-model MEX and produced finite discharge and Jacobian values. Source/dependency and GUI startup checks passed. Full training through the final GUI and installation on a clean Windows machine have not been independently verified in this release preparation. macOS v1.0.3 binaries are not included yet; they require a separate macOS build. The macOS v1.0.2 downloads remain available on the previous release.

View source

Similar papers

#computer vision Review Sep 2017

Agile Software Development Methods: Review and Analysis

This publication proposes a definition and a classification of agile software development approaches and analyses ten software development methods that can be characterized as being "agile" against the defined criterion.

P. Abrahamsson, O. Salo, Jussi Ronkainen et al. · 727 citations · ⚡54
#computer vision Jun 2008

The impact of agile practices on communication in software development

The study shows that agile practices improve both informal and formal communication, but indicates that, in larger development situations involving multiple external stakeholders, a mismatch of adequate communication mechanisms can sometimes even hinder the communication.

M. Pikkarainen, Jukka Haikara, O. Salo et al. · 401 citations · ⚡48
#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54
#computer vision Review Mar 2008

Agile methods in European embedded software development organisations: a survey on the actual use and usefulness of Extreme Programming and Scrum

The results show that the embedded industry has been able to apply agile methods in its development processes and that the appreciation of the agile methods and their individual practices appears to increase once adopted and applied in practice.

O. Salo, P. Abrahamsson · 238 citations · ⚡9
#computer vision Open access Jul 2017

What happens when software developers are (un)happy

Consequences of happiness and unhappiness that are beneficial and detrimental for developers' mental well-being, the software development process, and the produced artifacts are found.

D. Graziotin, Fabian Fagerholm, Xiaofeng Wang et al. · 236 citations · ⚡13
#computer vision Open access Oct 2004

Mobile-D: an agile approach for mobile application development

The Mobile-D approach is briefly outlined here and the experiences gained from four case studies are discussed, which helped develop an agile development approach for mobile application development.

P. Abrahamsson, Antti Hanhineva, H. Hulkko et al. · 225 citations · ⚡18

Related blog posts

MIT News · Artificial Intelligence Oct 2, 2026

Documenting the tech worker movement

Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.

GPT-Lab Sep 23, 2026

Requirements Don’t Live in Isolation: What We’re Exploring with Req-Space

Requirements in large systems rarely exist in isolation. Their meaning depends on the wider project context - other requirements, policies, decisions, tests, and implementation details. That becomes especially important when AI is used for review, because spotting a possible conflict or gap is only the beginning. ReqSpace explores how AI, visualisation, and connected project context can help reviewers understand those findings, trace the relationships behind them, and focus on the questions that…

GPT-Lab Sep 17, 2026

Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering

AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.