In order to better realize rural revitalization, this paper analyzes the spatial and temporal char-acteristics and influencing factors of agricultural surface source pollution in the Yangtze River Economic Belt from the three perspectives of government, enterprise and agriculture by using the spatial Durbin model and the dynamic GMM method in the period of 2006-2021, and further re-searches the threshold characteristics of the distortion of the factor market on the agricultural surface source pollution under the different strengths of environmental regulation. The results show that there is a positive spatial correlation between agricultural surface pollution in the Yangtze River Economic Belt, and government environmental regulation, input factor market distortion and labor force transfer all have a significant impact on agricultural surface pollution. Among them, factor market distortion has a significant spatial spillover effect on agricultural surface pollution in the Yangtze River Economic Zone, and has a significant single-threshold ef-fect on environmental regulation. Accordingly, the government should strengthen environmental regulation, continuously improve the agricultural factor market mechanism, and pay attention to the construction of talents to provide support for rural revitalization.

Transposable elements (TEs) are mobile genetic elements capable of rapidly altering the genome through their movements. The importance of TE activity has been documented in many biological processes, such as introducing genetic instability, altering patterns of gene expression, and accelerating genome evolution. Increasing appreciation of TEs results in the growing number of bioinformatics software to identify insertion events. However, the application of existing TE finding tools is limited by either narrow-focused design of the package, too many dependencies on other tools, or prior knowledge required as input files that may not be readily available to all users. Here, we report a simple pipeline, TEfinder, developed for the detection of new TE insertions with minimal software dependencies using four inputs that can be easily generated with popular variant calling pipelines. The external software requirements are BEDTools, SAMtools, and Picard. Necessary inputs include TEs present in the reference genome, binary paired-end alignment, reference genome index, and a list of TE names. We tested TEfinder pipeline among several evolving populations of Fusarium oxysporum generated through a short-term adaptation study. Our results demonstrate that this easy-to-use tool can effectively detect new TE insertion events, making it accessible and practical for TE analysis.

Effective prediction of wastewater treatment is beneficial for precise control of wastewater treatment processes. The nonlinearity of pollutant indicators such as COD and TP makes the model difficult to fit and has low prediction accuracy. The classical deep learning methods have been shown to perform nonlinear modeling. However, there are enormous numerical differences between multi-dimensional data in the prediction problem of wastewater treatment, such as COD above 3000 mg/L and TP around 30 mg/L. It will make current normalization methods challenging to handle effectively, leading to the training failing to converge and the gradient disappears or exploding. This paper proposes a multi-factor prediction model based on deep learning. The model consists of a combined normalization layer and a codec. The combined normalization layer combines the advantages of three normalization calculation methods: z-score, Interval, and Max, which can realize the adaptive processing of multi-factor data, fully retain the characteristics of the data, and finally cooperate with the codec to learn the data characteristics and output the prediction results. Experiments show that the proposed model can overcome data differences and complex nonlinearity in predicting industrial wastewater pollutant indicators and achieve better prediction accuracy than classical models.

During the extraction of palm oil by smallholders in Cameroon, the use of enormous quantities of water results in palm oil mill effluent (POME), which contains substances that are deleterious to the environment at concentrations above the threshold values. A detailed description of the various processes involved is imperative so as to develop methods of reducing loss and minimising the environmental effect caused by the wastes produced. In this study, we characterise the small-holders’ palm oil production sector in Cameroon, along its entire production chain. The main demographics of smallholder farmers are adult males (64.4%) and married (46.7%) with low levels of formal education (51.1% attained only primary education). Plantation establishment involves deforestation of pristine vegetation (46.7%) as well as replacing other farming systems. Processing is carried out by the farmers with their own mills (48.9%) bought at exorbitant prices. Access to finances (51.1%) remains a key limitation to plantation expansion and the adoption of innovations in this sector. Workers’ health issues abound (75.6%) and are treated mainly using ethnomedicine (31.1%), and there is little or no social security; thus, sick workers generally pay their own bills (64.4%). Issues of environmental pollution from production to waste processing abound with solid waste mainly burnt (57.8%) and POME directed into open pits and streams (37.8%) where they become a nuisance and serve as breeding grounds for mosquitoes (51.1%); these issues will require greater state involvement for mitigation. Our findings suggest that farmers in the palm oil sector have deep knowledge base and competence, but government intervention are needed to stimulate further growth in this important sector.