JSJan Saynisch-Wagner

Jan Saynisch-Wagner

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jan Saynisch-Wagner has a total of 100 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Conditional updates of neural network weights for increased out of training performance

    by Jan Saynisch-Wagner, Saran Rajendran Sari

    This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. In contrast to previous approaches to out of distribution problems, which alter the inputs and outputs of an operator, our approach alters the operator itself. Here, we especially aim to alter the weights and biases of a neural network to mitigate the out of distribution problem. The method consists of three main steps: (1) Fine-tune a trained neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. (2) Choose reasonable predictors and derive a regression between the predictors and the noted weight anomalies. (3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three nonlinear use cases from the climate sciences, which include successful temporal, spatial, and cross-regime extrapolations of neural networks.

  • Open Access

    Detecting tsunami-generated magnetic fields using machine learning

    by Chiaki Mita, Takuto Minami, Jan Saynisch-Wagner, Aaron Hornschild, Hiroko Sugioka, Hiroaki Toh

  • Open Access

    From Natural Language to Reproducible Climate Analysis: FrevaGPT in the Geosciences

    by Gizem Ekinci, Koketso Molepo, Sebastian Willmann, Johanna Baehr, Kevin Sieck, Felix Oertel, Bianca Wentzel, Thomas Ludwig, Martin Bergemann, Jan Saynisch-Wagner, et al.

    Large language models (LLMs) have the potential to transform how climate scientists interact with data by lowering technical barriers and enabling more intuitive analysis workflows. Building on previous demonstrations of LLM-assisted climate analysis, we present how FrevaGPT, an LLM-powered scientific assistant integrated into Freva - a climate data search and analysis platform- , supports climate scientists in their day-to-day data exploration and analysis. FrevaGPT interprets natural language queries and automatically generates traceable, editable, and reusable analysis scripts that can be executed within established scientific environments. It retrieves relevant datasets and literature, performs analyses, and visualises results, therefore allowing researchers to focus on scientific interpretation rather than coding intricacies. By leveraging a broad repository of climate observations and model output, FrevaGPT ensures transparent and reproducible workflows that adhere to best practices in climate research. It also integrates seamlessly into Jupyter-AI and, by making use of the Freva library, combines the code-generating capabilities of LLMs with contextual understanding of how to access relevant datasets on the HPC cluster. As a “co-pilot” for geoscientists, the system not only responds to explicit requests but also proactively suggests relevant climate modes, events, and next analytical steps, helping to uncover insights that might otherwise be overlooked. Practical use cases demonstrate how FrevaGPT assists with interactive exploratory analysis and hypothesis refinement across climate datasets of varying complexity. By embedding LLM-assisted natural language interaction into real-world climate research workflows, this work highlights methodological considerations and opportunities for enhancing scientific productivity, promoting broader adoption of NLP and AI tools among Earth system scientists. We provide scientific evaluation of FrevaGPT’s capability through a benchmark suite. A live demo will be presented and can be used by the audience to do real climate analysis on a high-performance computer with access to petabytes of Earth system data - starting with a simple prompt.

  • Open Access

    Improving Dengue Forecasting with Spatiotemporal Data Augmentation and Machine Learning

    by Negar Siabi, Rackhun Son, Maik Thomas, Christopher Irrgang, Jan Saynisch Wagner

    Accurate forecasting of vector-borne diseases such as dengue is often challenged by limited and noisy spatiotemporal data. This study evaluates the effectiveness of data augmentation techniques in enhancing the robustness and predictive accuracy of machine learning models. We assess multiple augmentation strategies applied to weekly dengue case data across countries in South and Central America (2014–2022). Results show that augmentation substantially improves short-term forecasting performance, particularly in regions with sparse or irregular observations, yielding higher R² values and lower relative errors compared to non-augmented baselines. These findings demonstrate that well‑designed augmentation can mitigate data scarcity and strengthen the generalization of graph‑based deep learning frameworks for epidemiological forecasting. Overall, the study highlights augmentation as a practical and scalable approach for improving spatiotemporal ML applications in disease surveillance.

  • Open Access

    Development of an Observational Encoder for Data Assimilation in the Latent Space of a Variational Autoencoder (with Sea Surface Temperature)

    by Simone Carsey, Aaron Hornschild, Jan Saynisch-Wagner

    High-dimensional ocean datasets, e.g. of global sea surface temperature, provide crucial insight to the dynamic of physical ocean characteristics such as seasonal cycle, ENSO, and global trend, but the dimensionality often results in computational complexity. Deep learning methods, such as variational autoencoders (VAEs), offer dimension reduction techniques that retain nonlinearities while expressing the system state in a meaningful lower-dimensional latent space. We explore whether encoded spatially limited observations, such as from satellites, buoys, or ship tracks, could be assimilated in the latent space. First, we developed a VAE to create a low-dimensional representation of a global sea surface temperature anomalies dataset. Next, we built a sample environment to demonstrate data assimilation within the latent space by creating spatially incomplete observations from the global dataset by selecting specific regions and adding noise. Accordingly, we developed an observational encoder to map these observations into the latent space of the VAE. For the latent data assimilation, we created a Bayesian update (e.g. Kalman filter) and decoded assimilated observations to evaluate results. We report on the assimilation of encoded limited observations within the latent space and discuss possible applications and future development of this approach.

  • Open Access

    Reply on RC1-RC3

    by Jan Saynisch-Wagner, Saran Rajendran Sari

    This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three nonlinear use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks.

  • Open Access

    Comment on egusphere-2026-728

    by Jan Saynisch-Wagner, Saran Rajendran Sari

    This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three nonlinear use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks.

  • Open Access

    Comment on egusphere-2026-728

    by Jan Saynisch-Wagner, Saran Rajendran Sari

    This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three nonlinear use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks.

  • Open Access

    Comment on egusphere-2026-728

    by Jan Saynisch-Wagner, Saran Rajendran Sari

    This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three nonlinear use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks.

  • Open Access

    Conditional updates of neural network weights for increased out of training performance

    by Jan Saynisch-Wagner, Saran Rajendran Sari

    This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks.