<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  
  <title type="text" xml:lang="en"></title>
  <link type="application/atom+xml" href="http://mogren.one/feed.xml" rel="self"/>
   <link type="text" href="http://mogren.one" rel="alternate"/>
  <updated>2026-11-16T14:02:22+00:00</updated>
  <id>http://mogren.one</id>
  <author>
    <name>Olof Mogren</name>
  </author>
  <rights>Olof Mogren</rights>
  

  
  <entry>
    
    <title>Publication: From Adaptive to Automated Ecosystem Management</title>
    
    <link href="http://mogren.one/publications/2026/ecomgmt/"/>
    <updated>2026-10-09T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2026/ecomgmt/</id>
    <content type="html">Artificial Intelligence (AI) is dramatically changing our capacities to collect, make sense of, and act upon, large, diverse and evolving datasets. The power of AI systems lies in their architecture, with learning frameworks, models, data and automation together establishing closed loops between insights and actions. This conceptually resembles the idea behind Adaptive ecosystem management (AM), which builds on repeated data collection, modelling, forecasting and decision to continuously improve knowledge and goal fulfilment. In this paper, we ask how AI can help address existing gaps in AM. We show that AM increasingly uses AI technologies, but implementation has generally been piecemeal and focused on specific problems, rather than used as a comprehensive and integrated technology for systems change. We suggest that AI can support a next generation of iterative, self-learning, real-time automated AM systems. To reach that goal, we present a development roadmap and discuss implementation risks and uncertainties.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Multi-species distribution modeling using deep CNNs and satellite embeddings</title>
    
    <link href="http://mogren.one/publications/2026/sdms/"/>
    <updated>2026-09-07T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2026/sdms/</id>
    <content type="html">Traditional Species Distribution Models (SDMs) rely on coarse bioclimatic variables, struggling to capture localized ecological niches, habitat fragmentation, and multi-species interactions. This paper presents a high-resolution, multi-species deep learning framework modeling 34 terrestrial mammals across Sweden using opportunistic crowd-sourced data. We benchmark a deep convolutional neural network architecture (ResNet-18) against a spatial MLP (SINR) and Random Forest baselines. Crucially, integrating AlphaEarth Foundations (AEF) 64-dimensional satellite embeddings yields a performance improvement over traditional climate variables, pushing mean Average Precision (mAP) from 0.924 to 0.972. To counteract spatial observation biases inherent in presence-only records, we introduce a custom distance-density pseudo-absence generation mechanism. Models are evaluated across three distinct proxies: a held-out test split, an independent apex carnivore dataset (Rovbase), and expert range maps (IUCN Red List). Our results demonstrate that high-resolution satellite embeddings are essential for capturing fine-grained local landscape variations, accounting for human impacts, and maintaining robust performance under significant spatial distribution shifts.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: From Machine Learning to Large-Scale EO Products: Good Practices and Guidelines for Making Maps</title>
    
    <link href="http://mogren.one/publications/2026/from/"/>
    <updated>2026-07-27T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2026/from/</id>
    <content type="html">The past decade has seen an explosion of large-scale geospatial products derived from Earth observation (EO) data using machine learning (ML). Driven by expanding model capacity and compute availability, the domain has reached a level of operational maturity where practitioners can generate high-resolution global products spanning thematic areas as diverse as human settlement, vegetation structure, and natural hazards. Deep learning has expanded the paradigm beyond locally calibrated models toward singular, globally applicable models trained on heterogeneous data, attracting a broad and growing community of practitioners from both the EO and ML sides. Yet, the resulting workflow introduces challenges that fall between established EO practice and mainstream ML: every stage presents tightly coupled technical challenges that recur across applications, and much of the practical knowledge needed to navigate them remains siloed within individual application domains. This guide brings together map-makers across the EO and ML communities, distilling their common practices, recurring pitfalls, and recommended approaches into a single end-to-end account, from raw satellite data to a published map product. Crucially, it treats the pipeline as an integrated workflow rather than a sequence of independent steps. We focus on wall-to-wall raster maps at moderate resolution (10-30m) and continental to global extent, produced with ML from open satellite archives, mainly Sentinel-1, Sentinel-2 and Landsat. The article is written for a deliberately broad audience, from those just entering the EO domain to ML experts building ML-ready EO datasets or generating large-scale maps.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time</title>
    
    <link href="http://mogren.one/publications/2025/accuracy-cost/"/>
    <updated>2025-09-23T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2025/accuracy-cost/</id>
    <content type="html">Accurate labels are critical for deriving robust machine learning models. Labels are used to train supervised learning models and to evaluate most machine learning paradigms. In this paper, we model the accuracy and cost of a common weak labeling process where annotators assign presence or absence labels to fixed-length data segments for a given event class. The annotator labels a segment as &quot;present&quot; if it sufficiently covers an event from that class, e.g., a birdsong sound event in audio data. We analyze how the segment length affects the label accuracy and the required number of annotations, and compare this fixed-length labeling approach with an oracle method that uses the true event activations to construct the segments. Furthermore, we quantify the gap between these methods and verify that in most realistic scenarios the oracle method is better than the fixed-length labeling method in both accuracy and cost. Our findings provide a theoretical justification for adaptive weak labeling strategies that mimic the oracle process, and a foundation for optimizing weak labeling processes in sequence labeling tasks.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning</title>
    
    <link href="http://mogren.one/publications/2025/aggregation/"/>
    <updated>2025-03-04T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2025/aggregation/</id>
    <content type="html">The vast amounts of audio data collected in Sound Event Detection (SED) applications require efficient annotation strategies to enable supervised learning. Manual labeling is expensive and time-consuming, making Active Learning (AL) a promising approach for reducing annotation effort. We introduce Top K Entropy, a novel uncertainty aggregation strategy for AL that prioritizes the most uncertain segments within an audio recording, instead of averaging uncertainty across all segments. This approach enables the selection of entire recordings for annotation, improving efficiency in sparse data scenarios. We compare Top K Entropy to random sampling and Mean Entropy, and show that fewer labels can lead to the same model performance, particularly in datasets with sparse sound events. Evaluations are conducted on audio mixtures of sound recordings from parks with meerkat, dog, and baby crying sound events, representing real-world bioacoustic monitoring scenarios. Using Top K Entropy for active learning, we can achieve comparable performance to training on the fully labeled dataset with only 8% of the labels. Top K Entropy outperforms Mean Entropy, suggesting that it is best to let the most uncertain segments represent the uncertainty of an audio file. The findings highlight the potential of AL for scalable annotation in audio and time-series applications, including bioacoustics.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning</title>
    
    <link href="http://mogren.one/publications/2024/from/"/>
    <updated>2024-03-13T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2024/from/</id>
    <content type="html">In this work we propose an audio recording segmentation method based on an adaptive change point detection (A-CPD) for machine guided weak label annotation of audio recording segments. The goal is to maximize the amount of information gained about the temporal activation&apos;s of the target sounds. For each unlabeled audio recording, we use a prediction model to derive a probability curve used to guide annotation. The prediction model is initially pre-trained on available annotated sound event data with classes that are disjoint from the classes in the unlabeled dataset. The prediction model then gradually adapts to the annotations provided by the annotator in an active learning loop. The queries used to guide the weak label annotator towards strong labels are derived using change point detection on these probabilities. We show that it is possible to derive strong labels of high quality even with a limited annotation budget, and show favorable results for A-CPD when compared to two baseline query strategies.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning</title>
    
    <link href="http://mogren.one/publications/2024/impacts/"/>
    <updated>2024-03-07T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2024/impacts/</id>
    <content type="html">Land cover classification and change detection are two important applications of remote sensing and Earth observation (EO) that have benefited greatly from the advances of deep learning. Convolutional and transformer-based U-net models are the state-of-the-art architectures for these tasks, and their performances have been boosted by an increased availability of large-scale annotated EO datasets. However, the influence of different visual characteristics of the input EO data on a model&apos;s predictions is not well understood. In this work we systematically examine model sensitivities with respect to several color- and texture-based distortions on the input EO data during inference, given models that have been trained without such distortions. We conduct experiments with multiple state-of-the-art segmentation networks for land cover classification and show that they are in general more sensitive to texture than to color distortions. Beyond revealing intriguing characteristics of widely used land cover classification models, our results can also be used to guide the development of more robust models within the EO domain.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Efficient Node Selection in Private Personalized Decentralized Learning</title>
    
    <link href="http://mogren.one/publications/2024/efficient/"/>
    <updated>2024-01-09T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2024/efficient/</id>
    <content type="html">In this paper, we propose a novel approach for privacy-preserving node selection in personalized decentralized learning, which we refer to as Private Personalized Decentralized Learning (PPDL). Our method mitigates the risk of inference attacks through the use of secure aggregation while simultaneously enabling efficient identification of collaborators. This is achieved by leveraging adversarial multi-armed bandit optimization that exploits dependencies between the different arms. Through comprehensive experimentation on various benchmarks under label and covariate shift, we demonstrate that our privacy-preserving approach outperforms previous non-private methods in terms of model performance.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Concept-aware clustering for decentralized deep learning under temporal shift</title>
    
    <link href="http://mogren.one/publications/2023/concept-aware/"/>
    <updated>2023-06-22T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2023/concept-aware/</id>
    <content type="html">Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts. While non-iid data has been extensively studied in distributed settings, temporal shifts have received no attention. To the best of our knowledge, we are first with tackling the novel and challenging problem of decentralized learning with non-iid and dynamic data. We propose a novel algorithm that can automatically discover and adapt to the evolving concepts in the network, without any prior knowledge or estimation of the number of concepts. We evaluate our algorithm on standard benchmark datasets and demonstrate that it outperforms previous methods for decentralized learning.</content>
  </entry>
  

  
  <entry>
    
    <title>Talk: Tutorial at EUREF 2023: AI for the environment</title>
    
    <link href="http://mogren.one/talks/2023/euref/"/>
    <updated>2023-05-23T00:00:00+00:00</updated>
    <id>http://mogren.one/talks/2023/euref/</id>
    <content type="html"></content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas</title>
    
    <link href="http://mogren.one/publications/2023/dense-water-flow-intensity-prediction/"/>
    <updated>2023-04-05T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2023/dense-water-flow-intensity-prediction/</id>
    <content type="html"> Intensifying climate change will lead to more extreme weather events, including heavy rainfall and drought. Accurate stream flow prediction models which are adaptable and robust to new circumstances in a changing climate will be an important source of information for decisions on climate adaptation efforts, especially regarding mitigation of the risks of and damages associated with flooding. In this work we propose a machine learning-based approach for predicting water flow intensities in inland watercourses based on the physical characteristics of the catchment areas, obtained from geospatial data (including elevation and soil maps, as well as satellite imagery), in addition to temporal information about past rainfall quantities and temperature variations. We target the one-day-ahead regime, where a fully convolutional neural network model receives spatio-temporal inputs and predicts the water flow intensity in every coordinate of the spatial input for the subsequent day. To the best of our knowledge, we are the first to tackle the task of dense water flow intensity prediction; earlier works have considered predicting flow intensities at a sparse set of locations at a time. An extensive set of model evaluations and ablations are performed, which empirically justify our various design choices. Code and preprocessed data have been made publicly available at &lt;a href=&quot;https://github.com/aleksispi/fcn-water-flow&quot;&gt;this https URL&lt;/a&gt;. </content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Federated learning for performance prediction in multi-operator environments</title>
    
    <link href="http://mogren.one/publications/2023/multi-operator/"/>
    <updated>2023-02-15T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2023/multi-operator/</id>
    <content type="html">Telecom vendors and operators deliver services with strict requirements on performance, over complex and sometimes partly shared network infrastructures. A key enabler for network and service management in such environments is knowledge sharing, and the use of data-driven models for performance prediction, forecasting, and troubleshooting. In this paper, we outline a multi-operator service metrics prediction framework using federated learning that allows privacy-preserved knowledge-sharing across operators for improved model performance, and also reduced requirements on data transfer within an operator network. Federated learning is compared against local and central learning strategies for multi-operator performance prediction, and it is shown to balance the requirements on data privacy, model performance, and the network overhead. Further, the paper provides insights on how data heterogeneity affects model performance, where the conclusion is that standard federated learning has certain robustness to data heterogeneity. Finally, we discuss the challenges related to training a federated learning model with a limited budget on the communication rounds. The evaluation is performed using a set of realistic publicly available data traces, that are adapted specifically for the purpose of studying multi-operator service performance prediction.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Private Node Selection in Personalized Decentralized Learning</title>
    
    <link href="http://mogren.one/publications/2023/private/"/>
    <updated>2023-01-30T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2023/private/</id>
    <content type="html">In this paper, we propose a novel approach for privacy-preserving node selection in personalized decentralized learning, which we refer to as Private Personalized Decentralized Learning (PPDL). Our method mitigates the risk of inference attacks through the use of secure aggregation while simultaneously enabling efficient identification of collaborators. This is achieved by leveraging adversarial multi-armed bandit optimization that exploits dependencies between the different arms. Through comprehensive experimentation on various benchmarks under label and covariate shift, we demonstrate that our privacy-preserving approach outperforms previous non-private methods in terms of model performance.</content>
  </entry>
  

  
  <entry>
    
    <title>Publication: EFFGAN: Ensembles of fine-tuned federated GANs</title>
    
    <link href="http://mogren.one/publications/2022/effgan/"/>
    <updated>2022-12-17T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2022/effgan/</id>
    <content type="html"> Generative adversarial networks have proven to be a powerful tool for learning complex and high-dimensional data distributions, but issues such as mode collapse have been shown to make it difficult to train them. This is an even harder problem when the data is decentralized over several clients in a federated learning setup, as problems such as client drift and non-iid data make it hard for federated averaging to converge. In this work, we study the task of how to learn a data distribution when training data is heterogeneously decentralized over clients and cannot be shared. Our goal is to sample from this distribution centrally, while the data never leaves the clients. We show using standard benchmark image datasets that existing approaches fail in this setting, experiencing so-called client drift when the local number of epochs becomes to large. We thus propose a novel approach we call EFFGAN: Ensembles of fine-tuned federated GANs. Being an ensemble of local expert generators, EFFGAN is able to learn the data distribution over all clients and mitigate client drift. It is able to train with a large number of local epochs, making it more communication efficient than previous works. </content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Few-shot bioacoustic event detection using a prototypical network ensemble with adaptive embedding functions</title>
    
    <link href="http://mogren.one/publications/2022/fewshot/"/>
    <updated>2022-11-03T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2022/fewshot/</id>
    <content type="html"> In this report we present our method for the DCASE 2022 challenge on few-shot bioacoustic event detection. We use an ensemble of prototypical neural networks with adaptive embedding functions and show that both ensemble and adaptive embedding functions can be used to improve results from an average F-score of 41.3% to an average F-score of 60.0% on the validation dataset. </content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Financing Solutions for Circular Business Models: Exploring the Role of Business Ecosystems and Artificial Intelligence</title>
    
    <link href="http://mogren.one/publications/2022/financing/"/>
    <updated>2022-10-24T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2022/financing/</id>
    <content type="html"> Circular economy promotes a transition away from linear modes of production and consumption to systems with circular material flows that can significantly improve resource productivity. However, transforming linear business models to circular business models posits a number of financial consequences for product companies as they need to secure more capital in a stock of products that will be rented out over time and therefore will encounter a slower, more volatile cash flow in the short term compared to linear direct sales of products. This paper discusses the role of financial actors in circular business ecosystems and alternative financing solutions when moving from product-dominant business models to product-as-a-service or function-based business models and demonstrates a solution where state-of-the-art AI modelling can be incorporated for financial risk assessment. We provide an open implementation and a thorough empirical evaluation of an AI-model which learns to predict residual value of stocks of used items. Furthermore, the paper highlights solutions, managerial implications and potentials for financing circular business models, argues the importance of different forms of data in future business ecosystems, and puts forward recommendations for how AI can help overcoming some of the challenges ahead. </content>
  </entry>
  

  
  <entry>
    
    <title>Publication: A Novel Method for Smart Fire Detection Using Acoustic Measurements and Machine Learning: Proof of Concept</title>
    
    <link href="http://mogren.one/publications/2022/smartfiredetection/"/>
    <updated>2022-09-09T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2022/smartfiredetection/</id>
    <content type="html"> Fires are a major hazard resulting in high monetary costs, personal suffering, and irreplaceable losses. The consequences of a fire can be mitigated by early detection systems which increase the potential for successful intervention. The number of false alarms in current systems can for some applications be very high, but could be reduced by increasing the reliability of the detection system by using complementary signals from multiple sensors. The current study investigates the novel use of machine learning for fire event detection based on acoustic sensor measurements. Many materials exposed to heat give rise to acoustic emissions during heating, pyrolysis and burning phases. Further, sound is generated by the heat flow associated with the flame itself. The acoustic data collected in this study is used to define an acoustic sound event detection task, and the proposed machine learning method is trained to detect the presence of a fire event based on the emitted acoustic signal. The method is able to detect the presence of fire events from the examined material types with an overall F-score of 98.4%. The method has been developed using laboratory scale tests as a proof of concept and needs further development using realistic scenarios in the future. &lt;br /&gt;&lt;br /&gt; &lt;strong&gt;Editor&apos;s choice: Best paper award in The Journal of Fire Technology 2022.&lt;/strong&gt; &lt;a href=&quot;https://www.springer.com/journal/10694/updates/19267070&quot;&gt;More info.&lt;/a&gt; </content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Decentralized adaptive clustering of deep nets is beneficial for client collaboration</title>
    
    <link href="http://mogren.one/publications/2022/decentralized/"/>
    <updated>2022-07-23T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2022/decentralized/</id>
    <content type="html"> We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks. We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task. Our method does not rely on hyperparameters which are hard to estimate, such as the number of client clusters, but rather continuously adapts to the network topology using soft cluster assignment based on a novel adaptive gossip algorithm. We test the proposed method in various settings where data is not independent and identically distributed among the clients. The experimental evaluation shows that the proposed method performs better than previous state-of-the-art algorithms for this problem setting, and handles situations well where previous methods fail. </content>
  </entry>
  

  
  <entry>
    
    <title>Publication: Adversarial representation learning for synthetic replacement of private attributes</title>
    
    <link href="http://mogren.one/publications/2021/adversarial/"/>
    <updated>2021-12-15T00:00:00+00:00</updated>
    <id>http://mogren.one/publications/2021/adversarial/</id>
    <content type="html"> Data privacy is an increasingly important aspect of the analysis of big data for many real-world tasks. Privacy enhancing transformations of data can help unlocking the potential in data sources containing sensitive information, but finding the right balance between privacy and utility is often a tricky trade-off. In this work, we study how adversarial representation learning can be used to ensure the privacy of users, and to obfuscate sensitive attributes in existing datasets. While previous methods using this kind of approach only aim at obfuscating the sensitive information, we find that adding new information in its place strengthens the provided privacy. We propose a two step data privatization method that builds on generative adversarial networks: in the first step, sensitive data is removed from the representation, and in the second step, a sample which is independent of the input data is inserted in its place. The result is an approach that can provide stronger privatization on image data, and yet be preserving both the domain and the utility of the inputs. </content>
  </entry>
  

  
  <entry>
    
    <title>Talk: AI for environment at RISE</title>
    
    <link href="http://mogren.one/talks/2021/ai-for-climate/"/>
    <updated>2021-12-09T00:00:00+00:00</updated>
    <id>http://mogren.one/talks/2021/ai-for-climate/</id>
    <content type="html"></content>
  </entry>
  

</feed>

