the project and experiment planning module

the (zotero) literature module

process description language : pythonLab

universal, python based, automation language
gitlab.com/opensourcelab/pythonLab

pythonLabOrchestrator & Scheduler

gitlab.com/opensourcelab/pythonlabscheduler

pythonLabScheduler in the wild (stefan maak)

gitlab.com/opensourcelab/pythonlabscheduler

the data module

LabDataReader

https://gitlab.com/opensourcelab/LabDataReader

• generic data reader framework for propriatory (text based) data formats
• new data formats can be added as plugins
• rich meta data support
• automatic semantic annotation of the data
• fully written in python
• output formats: pandas data frame, JSON-LD, csv, (SciDat/AnIML - under development)

SciDat

gitlab.com/opensourcelab/ScientificData/SciDat

• efficient data and metadata storage for scientific / machine learning needs
• proper nullable data / missing data handling (pyarrow / parquet)
• data modalities, like range / limits, type / continuos / categorial ...
• fast exchange and loading (fastparquet, pyarrow, arrow flight)
• semantic annotations / metadata in RDF compliant format
• programming language agnostic
• commonly used in ETL pipelines (Apache Spark, prefect, ... )
• suitable for S3 file storage systems (MinIO)

build-in SPARQL interface

working with jupyter

building homgeneous infrastructure from ground up

... what software components are required ?

• device control
• data readout
• data transfer
• data storage
• semantic understanding of the data by the machines
• machine learning algorithms to "work on the data"
• feedback software to the instruments
• common description language
• process execution / scheduler

SiLA servers/devices of LARA

what are we trying to build ?

• generic software platform closed loop designs of the simple kind
• autonomous experiment design
• autonomous experiment exection
• autonomous experiment evaluation
• AI and machine learning
• redesign of the experiment
• continue this process until an desired outcome is reached or resources are used up

the challange

• full SiLA communication of all devices in all platforms
• platform independant process description language
• flexible programming language for complex processes
• dynamic and error tolerant scheduling
• full experimental metadata for machine learning applications
• storage and exchange of data between labs (KIWI biolab)
• fully semantic annotation of the metadata (ontologies)

benfits for machine learning applications

• rich metadata from ground up
• ontology based (s. ontology development workflow)
• allowing autonomous feature extraction

challanges to overcome

• heterogenous data
• non-standardised data structure
• non-standardised metadata - no semantics
• non-standardised device communication
• black-box software - closed source
• no advanced, comprehensive data storage

what is semantics enabled machine learning (ML) ?

• better "understanding" of the data by the ML algorithms
• semantics guided ML model building
  by automated feature extraction
• improved consitancy checking, because the ML algorithm can extract physical limits
• improved error handling, because the ML algorithm "knows" more about the predicted system

outlook

• simple idea, but implementation is not so simple
• simplification through (mobile) web apps
• voice control (e.g. OpenAI whisper)
• utilisation of LLMs for queries
• utilisation of evolving ontologies for consistancy and error checking

summary

• building a large, community driven open source infrastructure
• no black box, everything is adjustable and extendible
• advanced queries and automated feature extraction
• "robot scientist" - feedback loop driven science possible
• machine learing applications will dramatically improve, when the right metadata is in place
• we need a modern mind set (science and machine learning)
• we are not alone, please join and contribute !