Merge pull request #51 from amcaar/main

Add AI4EOSC and iMagine blog posts

Author: gmolto

content/english/blog/post-ai4eosc-summary.md

@@ -0,0 +1,71 @@
+---
+title: "Serverless Computing for Artificial Intelligence: The OSCAR–AI4EOSC Integration Story."
+date: 2025-11-10T09:00:00+01:00
+# post image
+image: "../../images/blog/post-ai4eosc/ai4eosc.svg"
+# post type (regular/featured)
+type: "featured"
+# meta description
+description: "OSCAR in the AI4EOSC project."
+# post draft
+draft: false
+---
+
+The [AI4EOSC](https://ai4eosc.eu/) European Project uses the OSCAR serverless platform to support the scalable execution of the inference phase of AI models. As the project has come to its end in August 2025, in this post, we want to briefly summarize the achievements and integrations performed during it.
+
+### What is AI4EOSC?
+
+[AI4EOSC](https://ai4eosc.eu/) stands for "Artificial Intelligence for the European Open Science Cloud." It is an initiative aimed at integrating artificial intelligence (AI) technologies into the [European Open Science Cloud (EOSC)](https://eosc.eu/), a federated ecosystem that enables researchers to access, process, and share data and services across Europe. 
+
+The AI4EOSC project focuses on simplifying how scientists develop, train, and deploy AI models. Thus, the main goal of AI4EOSC is to enhance the capabilities of EOSC by leveraging AI to improve data management, analysis, and sharing, thereby fostering innovation and collaboration in scientific research. Aligned with this aim, the project has successfully delivered the [AI4OS](https://github.com/ai4os) software stack and the [AI4EOSC Dashboard](https://dashboard.cloud.ai4eosc.eu/catalog/modules), where, among others, users can find the catalogue of available AI models and can easily deploy or re-train them.
+
+![AI4EOSC Dashboard screenshot](../../images/blog/post-ai4eosc/ai4eosc_dashboard.png)
+
+### OSCAR: The Serverless Solution for Inference of AI Models
+
+The scalable inference of AI models is performed by the AI4OS inference platform, which is based on the open-source serverless platform OSCAR. The AI4OS inference platform consists of a pre-deployed production instance of  the OSCAR cluster that is exclusively accessible to users belonging to the virtual organisation of AI4EOSC (vo.ai4eosc.eu). 
+
+OSCAR has evolved during the AI4EOSC project, and these are the key features we have developed during this collaboration:
+- Pre-trained AI models are delivered directly via OSCAR, ready for inference without additional setup. [More info](https://docs.ai4os.eu/en/latest/howtos/deploy/oscar.html).
+- Provided multiple execution modes: asynchronous (event-triggered), synchronous (HTTP requests), and exposed services (REST APIs).
+- Supported deployment on multi-cloud and edge devices (e.g., Raspberry Pi), with elastic scaling and integration with object storage (MinIO, dCache).
+- Enhanced privacy and multitenancy, with bucket management and Kubernetes secrets for secure data handling.
+- Streamlined authentication via integration with Keycloak for unified access control.
+- A redesigned dashboard, built with React, provides a user-friendly interface, while Prometheus and Grafana enable real-time monitoring and accounting.
+- Automated testing ensures reliability through Robot Framework acceptance tests, executed regularly via Jenkins pipelines.
+- Integration with [AI4Compose](https://github.com/ai4os/ai4-compose) for the execution of composite pipelines involving several AI models, created with a drag and drop approach (with Node-RED or Elyra).
+
+
+### Use Cases Integration
+
+The use cases of AI4EOSC have been using OSCAR for the deployment of their AI models for inference. Let's have a closer look at them to know how they have been using OSCAR.
+
+![AI4EOSC Use Cases](../../images/blog/post-ai4eosc/ai4eosc_usecases.png)
+
+##### UC1 - Agrometeorological forecasts
+
+In agriculture, timely weather insights are critical. This use case has developed an AI model that combines radar imagery, in-situ measurements and numerical weather predictions to provide timely and precise warnings for farmers and local communities. The OSCAR instance has been used to deploy multiple forecasting models (eight in total, one for each prediction lead time) as part of an [agrometeorological nowcasting pipeline](https://dashboard.cloud.ai4eosc.eu/catalog/modules/thunderstorm-nowcast-microstep). Here’s how it works:
+
+1. Input data are transferred from a forecasting virtual machine to the MinIO object storage system.
+2. This automatically triggers asynchronous inference on OSCAR.
+3. The model’s predictions are stored and transferred back, where they feed into a GeoServer to visualize warnings for farmers using a simple three-color (traffic light) system — and trigger notifications when needed.
+
+This workflow ensures automated, scalable, and real-time decision support for agricultural management. This work has been done in collaboration with the colleagues of [MicroStep-MIS](https://www.microstep-mis.com/).
+
+##### UC2 - Integrated plant protection scenario
+
+This use case has developed an AI model focused on the early detection of plant disease. The model combines a network of meteorological data, existing mathematical models and ground observations, enhanced with satellite data, to provide greater terrain coverage and spatial precision. Focused on a dataset directly taken from plants and crops of Poland, the model aims to improve the quality and safety of food production by reducing the usage of pesticides.
+
+A proof-of-concept integration with OSCAR has enabled a [plant protection application](https://dashboard.cloud.ai4eosc.eu/catalog/modules/integrated-plant-protection) to be deployed directly through the AI4EOSC marketplace. Researchers can test and experiment with this service using try-out deployments or containerized (Docker) access, paving the way for broader adoption in agricultural monitoring and pest management. This work has been done in collaboration with the colleagues of [PSNC](https://www.psnc.pl/).
+
+##### UC3 - Automated Thermography
+
+In the field of energy efficiency, two different AI models have been developed by this use case. The models apply Deep Learning techniques to detect hotspots through instance segmentation in combined thermal and RGB image data. OSCAR supports continuous inference for [Thermal Bridges on Building Rooftops Detection (TBBRDet)](https://dashboard.cloud.ai4eosc.eu/catalog/modules/thermal-bridges-rooftops-detector) model.
+Through a secure and user-friendly interface, building owners or urban planners can analyze thermographic data to detect energy losses — all without sharing raw data or inference results. 
+
+This demonstrates OSCAR’s privacy-preserving design: enabling powerful AI analysis while keeping sensitive information under control. This work has been done in collaboration with the colleagues of [KIT](https://www.kit.edu/).
+
+### Conclusion
+The integration of OSCAR into the AI4EOSC ecosystem marks a major step toward democratizing access to AI infrastructure for European researchers. By combining serverless computing with open science principles, it empowers scientific communities to deploy, test, and scale AI models efficiently and transparently.
+
+[OSCAR](https://grycap.github.io/oscar/) is developed by the [GRyCAP](https://www.grycap.upv.es/) research group at the [Universitat Politècnica de València](https://www.upv.es/). [AI4EOSC](https://ai4eosc.eu/) has received funding from the European Union's Horizon Europe 2022 research and innovation programme under agreement #101058593.

content/english/blog/post-imagine-summary.md

@@ -0,0 +1,57 @@
+---
+title: "Bringing Serverless to Marine Science: Our Journey with OSCAR and iMagine."
+date: 2025-11-11T09:00:00+01:00
+# post image
+image: "../../images/blog/post-imagine/imagine.png"
+# post type (regular/featured)
+type: "featured"
+# meta description
+description: "OSCAR in the iMagine project."
+# post draft
+draft: false
+---
+
+The [iMagine](https://www.imagine-ai.eu/) European Project uses the OSCAR serverless platform to support the scalable execution of the inference phase of marine AI models in mature thematic services. As the project has finished recently (in August 2025), in this post, we want to highlight the achievements and 
+
+### What is iMagine?
+
+The [iMagine](https://www.imagine-ai.eu/) project is an EU-funded project with the mission to deploy, operate, validate, and promote a dedicated iMagine AI framework and platform connected to EOSC, giving researchers in aquatic sciences open access to a diverse portfolio of AI based image analysis services and image repositories from multiple RIs, working on and of relevance to the overarching theme of Healthy oceans, seas, coastal and inland waters. This AI framework is based on the [AI4OS](https://github.com/ai4os) software stack provided by the [AI4EOSC project](https://ai4eosc.eu/) (read our post for more details about AI4EOSC and the role of OSCAR in the project).
+
+![iMagine Dashboard screenshot](../../images/blog/post-imagine/imagine-dashboard.png)
+
+### OSCAR in Aquatic Sciences
+Different mature use cases were deployed in production for inference with OSCAR. All these use cases have developed their own AI models and have packaged them into Docker images that can be easily deployed in OSCAR. Let's have a look to some of them:
+
+##### Marine litter Assessment 
+This service analyses drone images, observing litter floating at surface waters in seas, rivers and lakes, and lying at beaches and shores, delivering standardised classified litter data sets, which are fit for purpose of environmental management and indicators.
+
+![iMagine Use Case 1 Litter assessment architecture](../../images/blog/post-imagine/imagine-uc1.png)
+
+The model, available at the [iMagine Marketplace](https://dashboard.cloud.imagine-ai.eu/catalog/modules/litter-assessment) has been deployed for inference in OSCAR. It has been used primarily by asynchronous calls that store outputs in MinIO.
+
+##### ZooProcess Service
+This use case has established an operational image handling service at the iMagine platform that ingests, stores, processes images of marine water samples taken by the Zooscan instrument and uploads the resulting regions of interest to the EcoTaxa platform for later taxonomic Identification. The service consists of two different AI models: the [Classifier](https://dashboard.cloud.imagine-ai.eu/catalog/modules/zooprocess-multiple-classifier) and the [Separator](https://dashboard.cloud.imagine-ai.eu/catalog/modules/zooprocess-multiple-separator), both available at the iMagine Marketplace.
+
+The models have been deployed in OSCAR using “exposed services”. In that mode, the service’s API ([DEEPaaS API](https://github.com/ai4os/DEEPaaS)) is exposed outside of the underlying Kubernetes cluster. Therefore, users interact directly with the DEEPaaS API.
+
+##### AI-Powered Ecosystem Monitoring: the EMSO OBSEA use case
+This use case has developed a service at the iMagine platform for automatic processing of video imagery, collected by cameras at EMSO underwater OBSEA site, identifying and analysing different fish species. Moreover, at the EMSO-Obsea site, there was a significant unexploited image data collected from an underwater camera observing various fish species. The analysis of this data was a challenge, where thousands of images needed to be analysed by the [AI model](https://dashboard.cloud.imagine-ai.eu/catalog/modules/obsea-fish-detection). This is where OSCAR has played an important role.
+
+The usage of OSCAR in this use case was through [OSCAR Batch](https://github.com/grycap/oscar-batch), a tool specifically developed for this purpose to launch batches of tasks to the OSCAR cluster, thereby accelerating the analysis of historical images from the observatory. Thousands of images were thus analyzed in different tests and experiments, where the invocations received a compressed zip file containing the images to analyze.
+
+![iMagine OBSEA use case architecture integrated with OSCAR](../../images/blog/post-imagine/imagine-obsea.png)
+
+##### Flowcam Phytoplankton Identification 
+The Flowcam Phytoplankton Identification Service has been implemented through an AI model that analyzes and processes FlowCam images for determining taxonomic composition of phytoplankton samples. The model is available at the [iMagine Marketplace](https://dashboard.cloud.imagine-ai.eu/catalog/modules/phyto-plankton-classification). This model has been deployed in OSCAR for inference, tested both by synchronous and, more commonly, asynchronous calls, and it has been used in education. 
+
+In total, more than ~2.000 invocations were processed by the OSCAR cluster. These invocations took more than ~9,570 CPU hours.
+
+![iMagine Metrics collected by Grafana](../../images/blog/post-imagine/imagine-metrics.png)
+
+### Conclusion
+The iMagine project has demonstrated how serverless AI infrastructures like OSCAR can transform marine science by enabling scalable, automated, and privacy-preserving analysis of massive image datasets. By leveraging the OSCAR platform, researchers were able to focus on scientific innovation rather than computational complexity, accelerating discoveries in areas such as pollution monitoring, marine biodiversity, and ecosystem health.
+
+Although the project has officially concluded, its technological foundations, built on open, interoperable, and reusable components, will continue to support new research efforts within the European Open Science Cloud and beyond, fostering a sustainable future for AI-driven aquatic research.
+
+
+[OSCAR](https://grycap.github.io/oscar/) is developed by the [GRyCAP](https://www.grycap.upv.es/) research group at the [Universitat Politècnica de València](https://www.upv.es/). [iMagine](https://www.imagine-ai.eu/) has received funding from the European Union, Grant Agreement Number 101058625.