---
title: Cement Tracking with Satellites and Neural Networks
url: https://www.ml-quant.com/papers/repec/bfr-banfra-917/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:bfr:banfra:917
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fpublications.banque-france.fr%2Fsites%2Fdefault%2Ffiles%2Fmedias%2Fdocuments%2Fdt917.pdf%3Bh%3Drepec%3Abfr%3Abanfra%3A917
featured: 2023-07-19
citations: unknown
topic: ML & AI Methods
---


# Cement Tracking with Satellites and Neural Networks

A new three-step machine learning method for predicting world trade has been proposed, which outperforms traditional linear, non-linear techniques and other benchmark models.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fpublications.banque-france.fr%2Fsites%2Fdefault%2Ffiles%2Fmedias%2Fdocuments%2Fdt917.pdf%3Bh%3Drepec%3Abfr%3Abanfra%3A917
- Identifier: RePEc:bfr:banfra:917
- Released: 2023-07-19
- First featured: Quant Letter No. 8 (2023-07-19): https://www.ml-quant.com/issues/2023-07-19/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [Satellites Turn “Concrete”: Tracking Cement with Satellite Data and Neural Networks](https://www.ml-quant.com/papers/ssrn/4712741/): The study shows that using daily satellite images and machine learning to track economic activity is more effective than traditional models, particularly in the cement and construction industries.
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://www.ml-quant.com/papers/arxiv/2312.00752/): Sequence Modeling: Mamba, a neural network architecture that doesn't use attention or MLP blocks, provides faster inference and better performance in language, audio, and genomics than Transformers.
- [Graph Mamba: Towards Learning on Graphs with State Space Models](https://www.ml-quant.com/papers/arxiv/2402.08678/): Graph Mamba Networks, a new type of Graph Neural Networks, have been introduced, which achieve excellent performance in various benchmark datasets despite lower computational cost.
- [Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks](https://www.ml-quant.com/papers/arxiv/2310.02244/): Deep Residual Network Feature Learning: The research explores depthwise parametrizations in deep residual networks, pinpointing Depth-$\mu$P as the best parametrization for maximizing feature learning and diversity, but notes its limitations in deeper networks.
- [Edge Directionality Improves Learning on Heterophilic Graphs](https://www.ml-quant.com/papers/arxiv/2305.10498/): The study presents Directed Graph Neural Network (Dir-GNN), a new deep learning framework for directed graphs that surpasses traditional models in heterophilic benchmarks.
- [Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models](https://www.ml-quant.com/papers/arxiv/2310.13828/): Poisoning Attacks on Text-to-Image Models: The article introduces Nightshade, an attack on text-to-image models that can disrupt their functionality, potentially serving as a defense against web scrapers.