Large-scale School Mapping using Weakly Supervised Deep Learning for Universal School Connectivity

• URL: http://arxiv.org/abs/2412.14870v1
• Date: Thu, 19 Dec 2024 14:06:56 GMT
• Title: Large-scale School Mapping using Weakly Supervised Deep Learning for Universal School Connectivity
• Authors: Isabelle Tingzon, Utku Can Ozturk, Ivan Dotu,
• Abstract summary: We propose a cost-effective, scalable approach to locating schools in high-resolution satellite images using weakly supervised deep learning techniques. Our best models, which combine vision transformers and convolutional neural networks, achieve AUPRC values above 0.96 across 10 pilot African countries.
• Score: 0.0
• License:
• Abstract: Improving global school connectivity is critical for ensuring inclusive and equitable quality education. To reliably estimate the cost of connecting schools, governments and connectivity providers require complete and accurate school location data - a resource that is often scarce in many low- and middle-income countries. To address this challenge, we propose a cost-effective, scalable approach to locating schools in high-resolution satellite images using weakly supervised deep learning techniques. Our best models, which combine vision transformers and convolutional neural networks, achieve AUPRC values above 0.96 across 10 pilot African countries. Leveraging explainable AI techniques, our approach can approximate the precise geographical coordinates of the school locations using only low-cost, classification-level annotations. To demonstrate the scalability of our method, we generate nationwide maps of school location predictions in African countries and present a detailed analysis of our results, using Senegal as our case study. Finally, we demonstrate the immediate usability of our work by introducing an interactive web mapping tool to streamline human-in-the-loop model validation efforts by government partners. This work successfully showcases the real-world utility of deep learning and satellite images for planning regional infrastructure and accelerating universal school connectivity.

Related papers

• Predicting Internet Connectivity in Schools: A Feasibility Study Leveraging Multi-modal Data and Location Encoders in Low-Resource Settings [1.7111728540102638]
  We present our work on school internet connectivity prediction using EO and ML. We find that ML with EO and ground-based auxiliary data yields the best performance in both countries, for accuracy, F1 score, and False Positive rates. Our work showcases a practical approach to support data-driven digital infrastructure development in low-resource settings.
  arXiv  Detail & Related papers  (2024-12-13T20:20:29Z)
• Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps [3.606726772030176]
  In 2023, 58.0% of the African population experienced moderate to severe food insecurity, with 21.6% facing severe food insecurity. We propose a data-centric framework with a teacher-student model setup, which uses diverse data sources to produce local land-cover maps. Our framework achieved higher quality maps, with improvements of 0.14 in the F1 score and 0.21 in Intersection-over-Union, compared to the best global model.
  arXiv  Detail & Related papers  (2024-12-01T11:48:58Z)
• Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition [24.701574433327746]
  We investigate the feasibility of probing a large language model for geography-based object knowledge. We propose geography knowledge regularization to ensure that soft prompts trained on a source set of geographies generalize to an unseen target set. Accuracy gains over prompting baselines on DollarStreet are up to +2.8/1.2/1.6 on target data from Africa/Asia/Americas, and +4.6 overall on the hardest classes.
  arXiv  Detail & Related papers  (2024-01-03T01:11:16Z)
• FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street Views [1.7847474813778919]
  We use a Federated UNet model for Semantic of satellite and street view images. The accuracy was above 95% and we also brought in a significant model compression to over 17 times and 62 times for street View and satellite images respectively. Our proposed framework has the potential to be a game-changer in real-time tracking of climate change across the planet.
  arXiv  Detail & Related papers  (2022-12-05T12:14:00Z)
• Imposing Consistency for Optical Flow Estimation [73.53204596544472]
  Imposing consistency through proxy tasks has been shown to enhance data-driven learning. This paper introduces novel and effective consistency strategies for optical flow estimation.
  arXiv  Detail & Related papers  (2022-04-14T22:58:30Z)
• Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification [61.44538721707377]
  We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery. We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method. We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
  arXiv  Detail & Related papers  (2022-03-11T16:14:14Z)
• Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning [53.90317574898643]
  We propose a simple and general framework for self-supervised point cloud representation learning. Inspired by how human beings understand the world, we utilize knowledge distillation to learn both global shape information and the relationship between global shape and local structures. Our method achieves the state-of-the-art performance on linear classification and multiple other downstream tasks.
  arXiv  Detail & Related papers  (2022-02-09T02:51:59Z)
• Jalisco's multiclass land cover analysis and classification using a novel lightweight convnet with real-world multispectral and relief data [51.715517570634994]
  We present our novel lightweight (only 89k parameters) Convolution Neural Network (ConvNet) to make LC classification and analysis. In this work, we combine three real-world open data sources to obtain 13 channels. Our embedded analysis anticipates the limited performance in some classes and gives us the opportunity to group the most similar.
  arXiv  Detail & Related papers  (2022-01-26T14:58:51Z)
• CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning [62.65937719264881]
  Federated learning facilitates learning across clients without transferring local data on these clients to a central server. We propose a nonlinear quantization for compressed gradient descent, which can be easily utilized in federated learning. Our system significantly reduces the communication cost by up to three orders of magnitude, while maintaining convergence and accuracy of the training process.
  arXiv  Detail & Related papers  (2020-12-15T12:20:28Z)
• Population Mapping in Informal Settlements with High-Resolution Satellite Imagery and Equitable Ground-Truth [1.4414055798999759]
  We propose a generalizable framework for the population estimation of dense, informal settlements in low-income urban areas. We use equitable ground-truth data, which is gathered in collaboration with local communities. We propose a gridded population estimation model, enabling flexible and customizable spatial resolutions.
  arXiv  Detail & Related papers  (2020-09-17T16:37:32Z)
• A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence [48.67755344239951]
  We provide a comprehensive survey, and propose a new taxonomy for localization and mapping using deep learning. A wide range of topics are covered, from learning odometry estimation, mapping, to global localization and simultaneous localization and mapping. It is our hope that this work can connect emerging works from robotics, computer vision and machine learning communities.
  arXiv  Detail & Related papers  (2020-06-22T19:01:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.