Peanut leaf spot is a worldwide disease whose prevalence poses a major threat to peanut yield and quality, and accurate prediction models are urgently needed for timely disease management. In this study, we proposed a novel peanut leaf spot prediction method based on an improved long short-term memory (LSTM) model and multi-year meteorological data combined with disease survey records. Our method employed a combination of convolutional neural network (CNN) and LSTM to capture spatial-temporal patterns from the data and improve the model ability to recognize dynamic features of the disease. In addition, we introduced an attention mechanism module to enhance model performance by focusing on key features. Through several hyper-parameter optimization adjustments, we identified a peanut leaf spot disease condition index prediction model with a learning rate of 0.001, a number of cycles (Epochs) of 800, and an optimizer of Adma. The results showed that the integrated model demonstrated excellent prediction ability, obtaining an RMSE of 0.063 and an R2 of 0.951, which reduced the RMSE by 0.253 and 0.204, and raised the R2 by 0.155 and 0.122, respectively, compared to the single CNN and LSTM. Predicting the incidence and severity of peanut leaf spot disease based on the meteorological conditions and neural networks is feasible and valuable to help growers made accurate management decisions and reduced disease impacts through optimal fungicide application timing.

One third of fatal car accidents and so much tragedies are due to alcohol abuse. These sad numbers could be mitigated if everyone had access to a breathalyzer anytime and anywhere. Having a breathalyzer built into a phone or a wearable could be the way to get around the reluctance to carry a separate device. Towards this goal, we propose an inexpensive breathalyzer that could be integrated in the screen of mobile devices. Our technology is based on the evaporation rate of the fog produced by the breath on the phone screen, which increases as a function of the breath alcohol content. The device simply uses a photodiode placed on the side of the screen to measure the signature of the scattered light intensity from the phone display that is guided through the stress layer of the Gorilla glass screen. A part of the display light is coupled to the stress layer via the evanescent field induced at the edge of the breath microdroplets. We demonstrate that the intensity signature measured at the detector can be linked to the blood alcohol content. We fabricated a prototype in a smartphone case powered by the phone’s battery, controlled by an application software installed in the smartphone and tested it in real-world environments. Limitations and future work toward a fully operational device are discussed.

Interface solar steam generation (ISSG) are charming for its applications in desalination and wastewater treatment. Biomass is an attractive substrate for utilizing solar vapor evaporators because of its natural pore structure and water transportability. Polymers like polydopamine (PDA) and polypyrrole (PPy) with broadband spectrum absorption are fascinating in photothermal materials (PTMs). Herein, PDA coated daikon-based (PDA-DK) and PPy coated daikon-based (PPy-DK) PTMs have been exploited for solar steam generation. When polyethylene foam (PEF) was used as an insulating layer to limit heat loss from the PTMs to bulk water, the evaporation rate of PDA-DK and PPy-DK was raised from 0.82 kg m–2 h–1 and 0.96 kg m–2 h–1 to 1.50 kg m–2 h–1 and 1.60 kg m–2 h–1, respectively. Meanwhile, the corresponding photothermal conversion efficiency was increased to 89.01% and 98.97%, which was increased by nearly 40% under 1-sun irradiation. In addition, PDA-DK and PPy-DK exhibited remarkable stability for the solar steam generation without significant change through 15 cycles. Furthermore, PDA-DK and PPy-DK could effectively desalt seawater and purify dyeing wastewater. All the results indicate that PDA-DK and PPy-DK have great potential in real-world applications for solar steam generation.