Xinyan Fan

Agricultural field polygons within smallholder farming systems are essential to facilitate the collection of geo-spatial data useful for farmers, managers, and policymakers. However, the limited availability of training labels poses a challenge in developing supervised methods to accurately delineate field boundaries using Earth Observation (EO) data. This letter introduces an open data set for training and benchmarking machine learning methods to delineate agricultural field boundaries in polygon format. The large-scale data set consists of 439,001 field polygons divided into 62 tiles of approximately 5×5 km distributed across Vietnam and Cambodia, covering a range of fields and diverse landscape types. The field polygons have been meticulously digitized from satellite images, following a rigorous multi-step quality control process and topological consistency checks. Multi-temporal composites of Sentinel-2 (S2) images are provided to ensure cloud-free data. We conducted an experimental analysis testing a state-of-the-art Deep Learning (DL) workflow based on fully convolutional networks, contour closing, and polygonization. We anticipate that this large-scale data set will enable researchers to further enhance the delineation of agricultural fields in smallholder farms and to support the achievement of the Sustainable Development Goals (SDG). The data set can be downloaded from https://doi.org/10.17026/dans-xy6-ngg6.

In this study, Bacillus subtilis, Clostridium butyricum and Enterococcus faecalis were made into a probiotic complex (PC). The PC was supplemented in AA+ male broilers’ diets to investigate the effects of PC on broiler growth performance, carcass traits, blood indicators, harmful gas emissions in feces and microbiota. Three hundred and sixty 1-day-old AA+ male broilers with an average initial body weight (data) were randomly divided into 3 dietary treatments of 6 replicates each, with 20 birds per replicate. The control group (T0) was fed a basal diet, while the test groups (T1 and T2) were supplemented with 0.025 and 0.05% PC in the basal diet, respectively. The trail was 42 days. The results showed that the supplementation of 0.05% PC significantly (p < 0.05) improved average daily gain (ADG) and average daily feed intake (ADFI) of broilers from 22 to 42 days and 1–42 days. Compared to the control group, the breast rate was significantly higher in T2, and the thymic index was significantly higher than that in T1 treatment (p < 0.05). The addition of PC had no significant effects on antibody potency in broiler serum (p > 0.05), but significantly increased albumin and total protein content in serum (p < 0.05). The addition of PC reduced H₂S and NH₃ emissions in the feces; the levels of Escherichia coli and Salmonella in the feces were significantly reduced and the levels of Lactobacillus were increased. And the most significant results were achieved when PC was added at 0.05%. Correlation analysis showed a significant positive correlation (p < 0.05) between the levels of E. coli and Salmonella and the emissions of H₂S and NH₃. Conclusion: Dietary supplementation with a 0.05% probiotic complex could improve the growth performance of broilers and also reduced fecal H₂S and NH₃ emissions, as well as fecal levels of E. coli and Salmonella, and increased levels of Lactobacillus. Thus, PC made by Bacillus subtilis, Clostridium butyricum and Enterococcus faecalis is expected to be an alternative to antibiotics. And based on the results of this trial, the recommended dose for use in on-farm production was 0.05%.

In this article, we propose the mutual influence regression model (MIR) to establish the relationship between the mutual influence matrix of actors and a set of similarity matrices induced by their associated attributes. This model is able to explain the heterogeneous structure of the mutual influence matrix by extending the commonly used spatial autoregressive model while allowing it to change with time. To facilitate making inferences with MIR, we establish parameter estimation, weight matrices selection and model testing. Specifically, we employ the quasi-maximum likelihood estimation method to estimate unknown regression coefficients, and demonstrate that the resulting estimator is asymptotically normal without imposing the normality assumption and while allowing the number of similarity matrices to diverge. In addition, an extended BIC-type criterion is introduced for selecting relevant matrices from the divergent number of similarity matrices. To assess the adequacy of the proposed model, we further propose an influence matrix test and develop a novel approach in order to obtain the limiting distribution of the test. Finally, we extend the model to accommodate endogenous weight matrices, exogenous covariates, and both individual and time fixed effects, to broaden the usefulness of MIR. The simulation studies support our theoretical findings, and a real example is presented to illustrate the usefulness of the proposed MIR model.

For estimating the large covariance matrix with a limited sample size, we propose the covariance model with general linear structure (CMGL) by employing the general link function to connect the covariance of the continuous response vector to a linear combination of weight matrices. Without assuming the distribution of responses, and allowing the number of parameters associated with weight matrices to diverge, we obtain the quasi-maximum likelihood estimators (QMLE) of parameters and show their asymptotic properties. In addition, an extended Bayesian information criteria (EBIC) is proposed to select relevant weight matrices, and the consistency of EBIC is demonstrated. Under the identity link function, we introduce the ordinary least squares estimator (OLS) that has the closed form. Hence, its computational burden is reduced compared to QMLE, and the theoretical properties of OLS are also investigated. To assess the adequacy of the link function, we further propose the quasi-likelihood ratio test and obtain its limiting distribution. Simulation studies are presented to assess the performance of the proposed methods, and the usefulness of generalized covariance models is illustrated by an analysis of the US stock market.

Climate change strongly affects the hydro-mechanical properties of soil. Due to drought and heavy rainsthe soil is subjected to severe hydro-mechanical loads, that, in turn, alter the microstructure of the soil.The most affected area is the so-called vadose zone, the layer of soil situated between the ground surface andthe water table. Here the presence of vegetation has a strong impact, related to the elongation/expansionof the root architecture and the hydro-mechanical interactions with soil. Additionally, the presence of plantroots facilitate the evapotranspiration process from deeper soil layers.The research presents an experimental investigation, aimed to reproduce the typical hydro-mechanicalconditions as found in the vadose zone in controlled laboratory conditions. Drying-wetting cycles are inducedin soils samples, where maize plants are free to sprout and develop as well as in reference non-vegetatedsamples. The water content and distribution within the soil matrix are studied through 4D (3D+time)in-vivo x-ray computed tomography and effects on the soil-root microstructure are quantified with 3Dimage analysis. Those are correlated with above ground measurements such as fluorescence (through aspectroradiometer) that, in turn, provides leaf water potential, and the stomatal conductance that controlsthe evapotranspiration.

Automated monitoring systems with different temporal and spatial resolutions can achieve precision agriculture management. Unmanned aerial vehicle (UAV) systems open new possibilities for effectively characterizing the variability within cropping systems with high spatial and temporal resolution. In this study, a UAV with a low‐cost visible and near‐infrared camera assessed the spatial variability in the herbage biomass (BM) and leaf area index (LAI) in an Italian ryegrass field. Using multiple linear regression (MLR) models, high coefficients of determination (R²) and low root‐mean‐squared error (RMSE) values were obtained between the observed and predicted herbage BM (R² = 0.84, RMSE = 90.43 g m⁻²) and LAI (R² = 0.88, RMSE = 0.82). The MLR models successfully recovered high‐resolution spatial distributions of the herbage BM and LAI from the ortho‐photos. The reconstructed maps verified that the proposed method can effectively characterize spatial field variations and assess forage growth to optimize field‐level forage crop management.

This research was conducted to exploit the waste of used plant parts from the widely marketed moth orchid cultivar (Phalaenopsis Sogo Yukidian “V3”). Various extracts of roots, stems, and leaves were evaluated for total phenolics, total flavonoids, and antioxidant capacity. The bound extract from stems contained the highest total phenolics (5.092 ± 0.739 mg GAE (gallic acid equivalent)/g DW (dry weight)). The maximum total flavonoids (2.218 ± 0.021 mg RE (rutin equivalent)/g DW) were found in the hexane extract of leaves. Ethyl acetate extract from roots showed the greatest antioxidant activity compared to other extracts. Of these extracts, the IC₅₀ values of these samples were 0.070 mg/mL, and 0.450 mg/mL in a free radical 1,-diphenyl-picryl-hydrazyl (DPPH) assay and reducing power method, respectively. The lipid peroxidation inhibition (LPI) was found to be 94.2% using the β-carotene bleaching method. Five phenolic compounds including caffeic acid, syringic acid, vanillin, ellagic acid, and cinnamic acid were quantified by high performance liquid chromatography (HPLC). It is suggested that the roots of the hybrid Phalaenopsis Sogo Yukidian “V3” cultivar may be exploited as an effective source of antioxidants.

Concentrations of chlorophyll-a (Chl-a) and total suspended solids (TSS) are significant parameters used to assess water quality. The objective of this study is to establish a quantitative model for estimating the Chl-a and the TSS concentrations in irrigation ponds in Higashihiroshima, Japan, using field hyperspectral measurements and statistical analysis. Field experiments were conducted in six ponds and spectral readings for Chl-a and TSS were obtained from six field observations in 2014. For statistical approaches, we used two spectral indices, the ratio spectral index (RSI) and the normalized difference spectral index (NDSI), and a partial least squares (PLS) regression. The predictive abilities were compared using the coefficient of determination (R²), the root mean squared error of cross validation (RMSECV) and the residual predictive deviation (RPD). Overall, iterative stepwise elimination based on PLS (ISE–PLS), using the first derivative reflectance (FDR), showed the best predictive accuracy, for both Chl-a (R² = 0.98, RMSECV = 6.15, RPD = 7.44) and TSS (R² = 0.97, RMSECV = 1.91, RPD = 6.64). The important wavebands for estimating Chl-a (16.97% of all wavebands) and TSS (8.38% of all wavebands) were selected by ISE–PLS from all 501 wavebands over the 400–900 nm range. These findings suggest that ISE–PLS based on field hyperspectral measurements can be used to estimate water Chl-a and TSS concentrations in irrigation ponds.