Enhancing kelp forest detection in remote sensing images using crowdsourced labels with Mixed Vision Transformers and ConvNeXt segmentation models

Kelp forests, as foundation species, are vital to marine ecosystems, providing essential food and habitat for numerous organisms. This study explores the integration of crowdsourced labels with advanced artificial intelligence models to develop a fast and accurate kelp canopy detection pipeline using Landsat images. Building on the success of a machine learning competition, where this approach ranked third and performed consistently well on both local validation and public and private leaderboards, the research highlights the effectiveness of combining Mixed Vision Transformers (MIT) with ConvNeXt models. Training these models on various image sizes significantly enhanced the accuracy of the ensemble results. U-Net emerged as the best segmentation architecture, with UpperNet also contributing to the final ensemble. Key Landsat bands, such as ShortWave InfraRed (SWIR1) and Near-InfraRed (NIR), were crucial while altitude data was used in postprocessing to eliminate false positives on land. The methodology achieved a high detection rate, accurately identifying about three out of four pixels containing kelp canopy while keeping false positives low. Despite the medium resolution of Landsat satellites, their extensive historical coverage makes them effective for studying kelp forests. This work also underscores the potential of combining machine learning models with crowdsourced data for effective and scalable environmental monitoring. All running code for training all models and inference can be found at https://github.com/IoannisNasios/Kelp_Forests.

Citizen participation: crowd-sensed sustainable indoor location services

In the present era of sustainable innovation, the circular economy paradigm dictates the optimal use and exploitation of existing finite resources. At the same time, the transition to smart infrastructures requires considerable investment in capital, resources and people. In this work, we present a general machine learning approach for offering indoor location awareness without the need to invest in additional and specialised hardware. We explore use cases where visitors equipped with their smart phone would interact with the available WiFi infrastructure to estimate their location, since the indoor requirement poses a limitation to standard GPS solutions. Results have shown that the proposed approach achieves a less than 2m accuracy and the model is resilient even in the case where a substantial number of BSSIDs are dropped.

Blending gradient boosted trees and neural networks for point and probabilistic forecasting of hierarchical time series

In this paper we tackle the problem of point and probabilistic forecasting by describing a blending methodology of machine learning models that belong to gradient boosted trees and neural networks families. These principles were successfully applied in the recent M5 Competition on both Accuracy and Uncertainty tracks. The keypoints of our methodology are: a) transform the task to regression on sales for a single day b) information rich feature engineering c) create a diverse set of state-of-the-art machine learning models and d) carefully construct validation sets for model tuning. We argue that the diversity of the machine learning models along with the careful selection of validation examples, where the most important ingredients for the effectiveness of our approach. Although forecasting data had an inherent hierarchy structure (12 levels), none of our proposed solutions exploited that hierarchical scheme. Using the proposed methodology, our team was ranked within the gold medal range in both Accuracy and the Uncertainty track. Inference code along with already trained models are available at https://github.com/IoannisNasios/M5_Uncertainty_3rd_place

Analyze Mass Spectrometry data with Artificial Intelligence to assist the understanding of past habitability of Mars and provide insights for future missions

This paper presents an application of artificial intelligence on mass spectrometry data for detecting habitability potential of ancient Mars. Although data was collected for planet Mars the same approach can be replicated for any terrestrial object of our solar system. Furthermore, proposed methodology can be adapted to any domain that uses mass spectrometry. This research is focused in data analysis of two mass spectrometry techniques, evolved gas analysis (EGA-MS) and gas chromatography (GC-MS), which are used to identify specific chemical compounds in geological material samples. The study demonstrates the applicability of EGA-MS and GC-MS data to extra-terrestrial material analysis. Most important features of proposed methodology includes square root transformation of mass spectrometry values, conversion of raw data to 2D sprectrograms and utilization of specific machine learning models and techniques to avoid overfitting on relative small datasets. Both EGA-MS and GC-MS datasets come from NASA and two machine learning competitions that the author participated and exploited. Complete running code for the GC-MS dataset/competition is available at GitHub.1 Raw training mass spectrometry data include [0, 1] labels of specific chemical compounds, selected to provide valuable insights and contribute to our understanding of the potential past habitability of Mars.