About
👩💻 In recent years, I have developed cloud-based products across the stack (React/React Native, Node/Python, SQL/big data, ML, AWS/Open Source). Most recently I've helped launch 𝐢𝐦𝐰𝐞𝐚𝐭𝐡𝐞𝐫.𝐜𝐨𝐦, which handles multiple TBs of weather data scalably every day.
🧠 Wrote 200+ tutorials about AI/ML available for free at 🔹 𝐦𝐚𝐜𝐡𝐢𝐧𝐞𝐜𝐮𝐫𝐯𝐞.𝐜𝐨𝐦. I'm happy to find that they are useful to many and used in publications/courses by people at CERN, Stanford University and other places.
👪 I like growing peoples' expertise in technology topics through educating and mentoring.
🍅🥐⚡ In my spare time, I get energized by chasing thunderstorms, making good food (pasta, pizza, bread, beer) and spending time in nature.
I currently work on weather technology at 🟢 infoplaza, known for Weerplaza, Weeronline and Buienalarm.
Articles by Christian
-
Een klassiek geval van disruptieve innovatie?
Een klassiek geval van disruptieve innovatie?
By Christian Versloot
Activity
-
After discussing the MLWP internals in our previous article (➡ https://lnkd.in/em-Vg-yW), this time, we focus a bit more on Pangu-Weather, GraphCast…
After discussing the MLWP internals in our previous article (➡ https://lnkd.in/em-Vg-yW), this time, we focus a bit more on Pangu-Weather, GraphCast…
Shared by Christian Versloot
-
From news.ycombinator.com: "In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on…
From news.ycombinator.com: "In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on…
Shared by Christian Versloot
-
The EU AI Act is a maze and we are running out of time, so we made a map to accelerate compliance. It is FREE and OPEN and for EVERYONE. Download…
The EU AI Act is a maze and we are running out of time, so we made a map to accelerate compliance. It is FREE and OPEN and for EVERYONE. Download…
Liked by Christian Versloot
Experience
Education
Licenses & Certifications
Publications
-
AI in het weer: een vlucht voorwaarts
Meteorologica
Kunstmatige intelligentie (AI) wekt wereldwijd interesse en wordt steeds vaker gebruikt in de meteorologie. In de
afgelopen jaren is de schaalgrootte hiervan veranderd: van nichetoepassingen zijn we naar datagedreven weermodel-
len gegaan, die door middel van patroonherkenning de prestaties van traditionele numerieke weermodellen (NWP-mo-
dellen) proberen te benaderen en verbeteren. In dit artikel gaan we dieper op deze materie in. Doel is om de lezer mee
te nemen in AI en de…Kunstmatige intelligentie (AI) wekt wereldwijd interesse en wordt steeds vaker gebruikt in de meteorologie. In de
afgelopen jaren is de schaalgrootte hiervan veranderd: van nichetoepassingen zijn we naar datagedreven weermodel-
len gegaan, die door middel van patroonherkenning de prestaties van traditionele numerieke weermodellen (NWP-mo-
dellen) proberen te benaderen en verbeteren. In dit artikel gaan we dieper op deze materie in. Doel is om de lezer mee
te nemen in AI en de toepassing ervan binnen de meteorologie, op zowel kleinschalig als globaal niveau.
Allereerst worden de ontwikkelingen in perspectief geplaatst. Waar hebben we het eigenlijk over, als het gaat over
‘AI’, ‘machine learning’ of ‘deep learning’? En hoe werkt het eigenlijk, het trainen van zo’n model? Met die basis
kijken we vervolgens naar kleinschalige meteorologische toepassingen, zoals die voor het nowcasten van extreme
weersverschijnselen als onweer of het simuleren van parameterisaties in NWP-modellen.
Naast kleinschalige toepassingen is sinds een jaar of twee echter ook een geheel nieuwe ontwikkeling gaande: die
van MLWP, oftewel Machine Learning Weather Prediction, als tegenhanger van NWP. Globale AI-modellen, getraind
op analyses van de atmosfeer, lijken in sommige gevallen beter te presteren dan NWP-modellen, ondanks verschillen-
de beperkingen. Op basis van de eerste generatie MLWP-modellen, die in dit artikel de revue passeren, wordt nieuw
onderzoek verricht om deze te overbruggen. Een grote hoeveelheid investeringen, bijvoorbeeld van ECMWF – dat de
ontwikkelingen als mogelijke rivaal voor NWP ziet (ECMWF, 2023b) – draagt daar significant aan bij. -
Supporting Utility Mapping With a Deep Learning Driven Analysis Tool
Emerald Publishing Limited
Utility strikes have spawned companies specializing in providing a priori analyses of the underground. Geophysical techniques such as Ground Penetrating Radar (GPR) are harnessed for this purpose. However, analyzing GPR data is labour-intensive and repetitive. It may therefore be worthwhile to amplify this process by means of Machine Learning (ML). In this work, harnessing the ADR design science methodology, an Intelligence Amplification (IA) system is designed that uses ML for decision-making…
Utility strikes have spawned companies specializing in providing a priori analyses of the underground. Geophysical techniques such as Ground Penetrating Radar (GPR) are harnessed for this purpose. However, analyzing GPR data is labour-intensive and repetitive. It may therefore be worthwhile to amplify this process by means of Machine Learning (ML). In this work, harnessing the ADR design science methodology, an Intelligence Amplification (IA) system is designed that uses ML for decision-making with respect to utility material type. It is driven by three novel classes of Convolutional Neural Networks (CNNs) trained for this purpose, which yield accuracies of 81.5% with outliers of 86%. The tool is grounded in the available literature on IA, ML and GPR and is embedded into a generic analysis process. Early validation activities confirm its business value.
Languages
-
Nederlands
Native or bilingual proficiency
-
Engels
Full professional proficiency
-
Frans
Limited working proficiency
-
Duits
Elementary proficiency
More activity by Christian
-
Nothing's as painful as staying stuck somewhere you don't belong. 🎓 Ready to embrace a new way of working and transform your team? Enroll for our…
Nothing's as painful as staying stuck somewhere you don't belong. 🎓 Ready to embrace a new way of working and transform your team? Enroll for our…
Liked by Christian Versloot
-
Interpretability has been a major criticism of neural networks. Can AI models learn physical laws and remain interpretable? I think they…
Interpretability has been a major criticism of neural networks. Can AI models learn physical laws and remain interpretable? I think they…
Liked by Christian Versloot
-
Dinsdagavond waren er mooie onweersbuien te zien boven de stad. Ook vanavond gaat het flink spoken...📸⚡ #nijmegen #gelderland #onweer…
Dinsdagavond waren er mooie onweersbuien te zien boven de stad. Ook vanavond gaat het flink spoken...📸⚡ #nijmegen #gelderland #onweer…
Liked by Christian Versloot
-
Today, the SNSPOOL received its CO2 reduction certificate from FincoEnergies-Marine manager Jeroen van Essen. As Fleet Manager Peterson Den Helder…
Today, the SNSPOOL received its CO2 reduction certificate from FincoEnergies-Marine manager Jeroen van Essen. As Fleet Manager Peterson Den Helder…
Liked by Christian Versloot
-
It seems to take about 2 years to get a B2B product to product market fit. I have started a few, invested in some and been on the board of other…
It seems to take about 2 years to get a B2B product to product market fit. I have started a few, invested in some and been on the board of other…
Liked by Christian Versloot
-
Another amazing day on the Simply-Bread.co Spring Road trip! Yesterday, we visited Morgan from @Wildlybaked in Southwest Missouri. Morgan lives on a…
Another amazing day on the Simply-Bread.co Spring Road trip! Yesterday, we visited Morgan from @Wildlybaked in Southwest Missouri. Morgan lives on a…
Liked by Christian Versloot
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Christian Versloot
1 other named Christian Versloot is on LinkedIn
See others named Christian Versloot