Browse Articles

Domestic waste classification using convolutional neural network

In this study, the authors investigate whether Moringa Oleifera seeds can serve as material to aid in purifying water. M. oleifera seeds have coagulating properties and the authors hypothesized that including it in a water filtration system would reduce particles, specifically bacteria, in water. Their results show that this system removed the largest percent of bacteria. When used in combination with cilantro, it was actually more efficient than the other techniques! These findings have important implications for creating better and more economical water purification systems.

Here the authors investigated the effectiveness of algal pretreatment in reducing nitrate toxicity and extending the survival of fish in contaminated river water. Their findings demonstrate that treating nitrate-polluted water with algae extended fish survival by up to 50%, suggesting that algae could serve as a valuable tool for mitigating the destructive impacts of agricultural and industrial runoff on aquatic ecosystems.

Multi-perspective drone imagery (adding oblique views to top-down shots) raised crop classification accuracy from 35.73% to 52.93% across five species. The improvement scaled with canopy complexity, from +4.2% for simple rice to +38.1% for structurally complex sugarcane.

The authors monitored water quality over time looking for influences from construction and deforestation.

We developed new eco-friendly membranes enriched with natural nanomaterials to clean iron and manganese from drinking water. Some nanocomposite membranes achieved over 95% metal removal while maintaining water flux, suggesting improved performance compared to the undoped control group.

When granular materials are poured onto a surface, they form conical piles whose slopes increase before reaching a stable angle of repose. We found that this angle evolution follows a previously unrecognized two-phase exponential growth pattern that is conserved across granular materials with diverse particle properties. The parameters of this model correlate with particle friction and are influenced by deposition conditions, providing a quantitative framework for describing pile formation.

Tax incentives for sustainable technology are a key part of the push for a greener future. However, these incentives may not reach all income strata equally. Using a machine learning approach, this study analyzed the distributional effects of residential energy tax credits across different income levels in the United States.

The authors investigated adoption rates of solar photovoltaic power at K-12 schools in California.

The authors investigated the impact of light pollution on astrophotography.