arXiv subjects

Jonathan Brandt

Publications and source records attributed to Jonathan Brandt.

15 recordsLinked to original sources

arXiv2026

Hybrid electrolyzer systems: Smart strategy or economic fallacy?

Hybrid electrolyzer systems combining alkaline water electrolysis and proton exchange membrane water electrolysis have been investigated in the literature motivated by the expectation that their contrary techno-economic characteristics compensate for the individual technical and economic restrictions of each technology, thereby improving the profitability of green hydrogen production. To reassess the economic potential of hybrid electrolyzer systems beyond these technology-specific assumptions, we independently vary two key characteristics, electrolyzer efficiency and investment cost, in a large-scale sensitivity analysis. For each generated parameter configuration, we performed a techno-economic optimization of a green hydrogen supply chain, including two electrolyzers. The resulting system design, cost objective, and dispatch behavior are subsequently analyzed. Consequently, hybrid electrolyzer systems are identified as optimal if they provide a cost benefit over single electrolyzer systems. The analysis reveals that hybrid electrolyzer systems represent the optimal solution in at most 5.0% of the investigated cases. Furthermore, the maximum cost benefit is 0.057 EUR/kgH2, which corresponds to only about 1% of the total green hydrogen production cost. Additional analyses considering variations in energy purchase prices, storage fees, availability of renewable energy, and baseline electrolyzer efficiency yield negligible changes to these results. Hence, considering that hybrid electrolyzer systems offer marginal cost benefits and prove economically optimal in very few cases, they seem more likely to represent an economic fallacy than a smart strategy.

cs.CE↗

arXiv2026

Mitigating business risks from renewable PPA power sourcing uncertainties for European green hydrogen production: Robust system design, regulatory adjustments and offtake flexibility

As energy prices surge for the second time in recent years driven by the ongoing crisis in the Middle East, the European Union's continuing reliance on fossil energy imports is becoming increasingly apparent. However, despite offering an intriguing prospect of improved energy resilience, the ramp-up of local green hydrogen production lags far behind the officially stated ambitions set after the 2022 energy crisis. A prominent reason for the widening implementation gap between announced and realised production projects is overly strict rules on renewable power sourcing, prompting Member states' ministries and the European Commission to propose advancing a planned rules review from 2028 to 2026. To contribute to a successful review and rule adjustments, we address an important gap in understanding the effects of power purchase rules on green hydrogen production. By taking the perspective of European electrolyser operators, we show how the criterion of additionality and its interaction with required temporal correlation can jeopardise the fulfilment of green hydrogen offtake agreements and affect green hydrogen production costs across different European bidding zones. Applying different design paradigms to a green hydrogen production system reveals that electrolyser operator measures, such as PPA and storage upsizing, can help to mitigate the business risks posed by the additionality criterion but come with increased costs. Alternatively, relaxed temporal correlation and increased offtake flexibility both increase production system robustness and reduce production costs simultaneously. Whereby relaxing temporal correlation rules does not result in exceeded emission intensity thresholds, underlining the potential of extended transitional rules to support the ramp-up of European green hydrogen production.

eess.SY↗

arXiv2025

Cost-optimized replacement strategies for water electrolysis systems affected by degradation

A key factor in reducing the cost of green hydrogen production projects using water electrolysis systems is to minimize the degradation of the electrolyzer stacks, as this impacts the lifetime of the stacks and therefore the frequency of their replacement. To create a better understanding of the economics of stack degradation, we present a linear optimization approach minimizing the costs of a green hydrogen supply chain including an electrolyzer with degradation modeling. By calculating the levelized cost of hydrogen depending on a variable degradation threshold, the cost optimal time for stack replacement can be identified. We further study how this optimal time of replacement is affected by uncertainties such as the degradation scale, the load-dependency of both degradation and energy demand, and the costs of the electrolyzer. The variation of the identified major uncertainty degradation scale results in a difference of up to 9 years regarding the cost optimal time for stack replacement, respectively lifetime of the stacks. Therefore, a better understanding of the degradation impact is imperative for project cost reductions, which in turn would support a proceeding hydrogen market ramp-up.

cs.CE↗

arXiv2025

Negative redispatch power for green hydrogen production: Game changer or lame duck? A German perspective

Following years of controversial discussions about the risks of market-based redispatch, the German transmission network operators finally installed regional redispatch markets by the end of 2024. Since water electrolysers are eligible market participants, the otherwise downwards redispatched renewable energy can be used for green hydrogen production in compliance with European law. To show how different price levels in regional redispatch markets affect green hydrogen production cost and thus the incentive for electrolyser market participation, we use historic redispatch time series and evaluate various power purchase scenarios. Our results show that low price levels can lead to notable production cost reductions, potentially counteracting uncertainties in redispatch power availability and thus incentivising system-beneficial electrolyser siting. In contrast, the possibility of high price levels can nullify an increase in the competitiveness of German and European green hydrogen through production cost reductions and discourage market participation.

q-fin.GN↗

arXiv2024

TurboEdit: Instant text-based image editing

We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

cs.CV↗

arXiv2021

StreamHover: Livestream Transcript Summarization and Annotation

With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge. However, the problem is nontrivial due to the informal nature of spoken language. Further, there has been a shortage of annotated datasets that are necessary for transcript summarization. In this paper, we present StreamHover, a framework for annotating and summarizing livestream transcripts. With a total of over 500 hours of videos annotated with both extractive and abstractive summaries, our benchmark dataset is significantly larger than currently existing annotated corpora. We explore a neural extractive summarization model that leverages vector-quantized variational autoencoder to learn latent vector representations of spoken utterances and identify salient utterances from the transcripts to form summaries. We show that our model generalizes better and improves performance over strong baselines. The results of this study provide an avenue for future research to improve summarization solutions for efficient browsing of livestreams.

cs.CL↗

arXiv2019

LPaintB: Learning to Paint from Self-Supervision

We present a novel reinforcement learning-based natural media painting algorithm. Our goal is to reproduce a reference image using brush strokes and we encode the objective through observations. Our formulation takes into account that the distribution of the reward in the action space is sparse and training a reinforcement learning algorithm from scratch can be difficult. We present an approach that combines self-supervised learning and reinforcement learning to effectively transfer negative samples into positive ones and change the reward distribution. We demonstrate the benefits of our painting agent to reproduce reference images with brush strokes. The training phase takes about one hour and the runtime algorithm takes about 30 seconds on a GTX1080 GPU reproducing a 1000x800 image with 20,000 strokes.

cs.LG↗

arXiv2019

PaintBot: A Reinforcement Learning Approach for Natural Media Painting

We propose a new automated digital painting framework, based on a painting agent trained through reinforcement learning. To synthesize an image, the agent selects a sequence of continuous-valued actions representing primitive painting strokes, which are accumulated on a digital canvas. Action selection is guided by a given reference image, which the agent attempts to replicate subject to the limitations of the action space and the agent's learned policy. The painting agent policy is determined using a variant of proximal policy optimization reinforcement learning. During training, our agent is presented with patches sampled from an ensemble of reference images. To accelerate training convergence, we adopt a curriculum learning strategy, whereby reference patches are sampled according to how challenging they are using the current policy. We experiment with differing loss functions, including pixel-wise and perceptual loss, which have consequent differing effects on the learned policy. We demonstrate that our painting agent can learn an effective policy with a high dimensional continuous action space comprising pen pressure, width, tilt, and color, for a variety of painting styles. Through a coarse-to-fine refinement process our agent can paint arbitrarily complex images in the desired style.

cs.CV↗

arXiv2019

Hotels-50K: A Global Hotel Recognition Dataset

Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 million annotated hotel room images from 50,000 hotels. These images include professionally captured photographs from travel websites and crowd-sourced images from a mobile application, which are more similar to the types of images analyzed in real-world investigations. We present a baseline approach based on a standard network architecture and a collection of data-augmentation approaches tuned to this problem domain.

cs.CV↗

arXiv2018

Learning to Sketch with Deep Q Networks and Demonstrated Strokes

Doodling is a useful and common intelligent skill that people can learn and master. In this work, we propose a two-stage learning framework to teach a machine to doodle in a simulated painting environment via Stroke Demonstration and deep Q-learning (SDQ). The developed system, Doodle-SDQ, generates a sequence of pen actions to reproduce a reference drawing and mimics the behavior of human painters. In the first stage, it learns to draw simple strokes by imitating in supervised fashion from a set of strokeaction pairs collected from artist paintings. In the second stage, it is challenged to draw real and more complex doodles without ground truth actions; thus, it is trained with Qlearning. Our experiments confirm that (1) doodling can be learned without direct stepby- step action supervision and (2) pretraining with stroke demonstration via supervised learning is important to improve performance. We further show that Doodle-SDQ is effective at producing plausible drawings in different media types, including sketch and watercolor.

cs.CV↗

arXiv2016

Top-down Neural Attention by Excitation Backprop

We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process. Furthermore, we introduce the concept of contrastive attention to make the top-down attention maps more discriminative. In experiments, we demonstrate the accuracy and generalizability of our method in weakly supervised localization tasks on the MS COCO, PASCAL VOC07 and ImageNet datasets. The usefulness of our method is further validated in the text-to-region association task. On the Flickr30k Entities dataset, we achieve promising performance in phrase localization by leveraging the top-down attention of a CNN model that has been trained on weakly labeled web images.

cs.CV↗

arXiv2015

DeepFont: Identify Your Font from An Image

As font is one of the core design concepts, automatic font identification and similar font suggestion from an image or photo has been on the wish list of many designers. We study the Visual Font Recognition (VFR) problem, and advance the state-of-the-art remarkably by developing the DeepFont system. First of all, we build up the first available large-scale VFR dataset, named AdobeVFR, consisting of both labeled synthetic data and partially labeled real-world data. Next, to combat the domain mismatch between available training and testing data, we introduce a Convolutional Neural Network (CNN) decomposition approach, using a domain adaptation technique based on a Stacked Convolutional Auto-Encoder (SCAE) that exploits a large corpus of unlabeled real-world text images combined with synthetic data preprocessed in a specific way. Moreover, we study a novel learning-based model compression approach, in order to reduce the DeepFont model size without sacrificing its performance. The DeepFont system achieves an accuracy of higher than 80% (top-5) on our collected dataset, and also produces a good font similarity measure for font selection and suggestion. We also achieve around 6 times compression of the model without any visible loss of recognition accuracy.

cs.CV↗

arXiv2015

Decomposition-Based Domain Adaptation for Real-World Font Recognition

We present a domain adaption framework to address a domain mismatch between synthetic training and real-world testing data. We demonstrate our method on a challenging fine-grain classification problem: recognizing a font style from an image of text. In this task, it is very easy to generate lots of rendered font examples but very hard to obtain real-world labeled images. This real-to-synthetic domain gap caused poor generalization to new real data in previous font recognition methods (Chen et al. (2014)). In this paper, we introduce a Convolutional Neural Network decomposition approach, leveraging a large training corpus of synthetic data to obtain effective features for classification. This is done using an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits a large collection of unlabeled real-world text images combined with synthetic data preprocessed in a specific way. The proposed DeepFont method achieves an accuracy of higher than 80% (top-5) on a new large labeled real-world dataset we collected.

cs.CV↗

arXiv2015

Real-World Font Recognition Using Deep Network and Domain Adaptation

We address a challenging fine-grain classification problem: recognizing a font style from an image of text. In this task, it is very easy to generate lots of rendered font examples but very hard to obtain real-world labeled images. This real-to-synthetic domain gap caused poor generalization to new real data in previous methods (Chen et al. (2014)). In this paper, we refer to Convolutional Neural Networks, and use an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits unlabeled real-world images combined with synthetic data. The proposed method achieves an accuracy of higher than 80% (top-5) on a real-world dataset.

cs.CV↗

arXiv2014

Scalable Similarity Learning using Large Margin Neighborhood Embedding

Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown promising results, especially when they are underpinned by a learned distance or similarity measurement. Although metric learning has been well studied in the past decades, most existing algorithms are impractical to handle large-scale data sets. In this paper, we present an image similarity learning method that can scale well in both the number of images and the dimensionality of image descriptors. To this end, similarity comparison is restricted to each sample's local neighbors and a discriminative similarity measure is induced from large margin neighborhood embedding. We also exploit the ensemble of projections so that high-dimensional features can be processed in a set of lower-dimensional subspaces in parallel without much performance compromise. The similarity function is learned online using a stochastic gradient descent algorithm in which the triplet sampling strategy is customized for quick convergence of classification performance. The effectiveness of our proposed model is validated on several data sets with scales varying from tens of thousands to one million images. Recognition accuracies competitive with the state-of-the-art performance are achieved with much higher efficiency and scalability.

cs.CV↗