Over the last few decades, a growing incidence of Banana Wilt (BW) has been detected in the banana-producing areas of the central zone of Venezuela. This disease is thought to be caused by a fungal–bacterial complex, coupled with the influence of specific soil properties. However, until now, there was no consensus on the soil characteristics associated with a high incidence of BW. The objective of this study was to identify the soil properties potentially associated with BW incidence, using supervised methods. The soil samples associated with banana plant lots in Venezuela, showing low (n = 29) and high (n = 49) incidence of BW, were collected during two consecutive years (2016 and 2017). On those soils, sixteen soil variables, including the percentage of sand, silt and clay, pH, electrical conductivity, organic matter, available contents of K, Na, Mg, Ca, Mn, Fe, Zn, Cu, S and P, were determined. The Wilcoxon test identified the occurrence of significant differences in the soil variables between the two groups of BW incidence. In addition, Orthogonal Least Squares Discriminant Analysis (OPLS-DA) and the Random Forest (RF) algorithm was applied to find soil variables capable of distinguishing banana lots showing high or low BW incidence. The OPLS-DA model showed a proper fitting of the data (R²Y: 0.61, p value < 0.01), and exhibited good predictive power (Q²: 0.50, p value < 0.01). The analysis of the Receiver Operating Characteristics (ROC) curves by RF revealed that the combination of Zn, Fe, Ca, K, Mn and Clay was able to accurately differentiate 84.1% of the banana lots with a sensitivity of 89.80% and a specificity of 72.40%. So far, this is the first study that identifies these six soil variables as possible new indicators associated with BW incidence in soils of lacustrine origin in Venezuela.

Accurate predictions of crop production are critical to developing effective strategies at the farm level. Knowing banana production is due to the need to maximize the investment–profit ratio, and the availability of this information in advance allows decisions to be made about the management of important diseases. The objective of this study was to predict the number of banana bunches from epidemiological parameters of Black Sigatoka (BS), using random forests (RF) for its ability to predict crop production responses to epidemiological variables. Weekly production data (number of banana bunches) and epidemiological parameters of BS from three adjacent banana sites in Panama during 2015–2018 were used. RF was found to be very capable of predicting the number of banana bunches, with variance explained as 70.0% and root mean square error (RMSE) of 1107.93 ± 22 of the mean banana bunches observed in the test case. The site, week, youngest leaf spotted and youngest leaf with symptoms in plants with 10 weeks of physiological age were found to be the best predictor group. Our results show that RF is an efficient and versatile machine learning method for banana production predictions based on epidemiological parameters of BS due to its high accuracy and precision, ease of use, and usefulness in data analysis.

The objective of this study was to analyze the relationships between the Visual Evaluation of Soil Structure (VESS) and soil properties that make its adoption widely used in agriculture. For this, 25 papers related to the VESS (2009-2022) were considered where the information of the authors, the soil property: bulk density (BD), total soil porosity (TP), soil penetration resistance (PR), macroporosity, microporosity, soil organic carbon (SOC), and mean weight diameter of stable aggregates (MWD). The sample size (n=120 cases), and the correlation coefficient were extracted. To measure this relationship, the correlation coefficient of all studies was contemplated. A meta-analysis was carried out to obtain a global measure of the correlation between the VESS and soil properties across the studies. In the first instance, a fixed effects model was fitted for the correlation (effect size, known as the response variable in the meta-analysis). Subsequently, a random effects model was fitted for the correlation, followed by a subgroup analysis according to soil properties, due to the presence of high heterogeneity between studies. The overall effect (average correlation coefficient) of the fitted random effects model was 0.31 with a confidence interval (CI) of [0.22;0.41]. The heterogeneity between studies was high ( =94.0%) and statistically significant p<0.001. Although it is moderate, the average correlation in practical terms may be sufficient. There were significant differences in some average correlations of some categories, such as BD, PR, TP, and microporosity. The weights reported for the BD, SOC, and PR were 29.7%, 16.4%, and 14.2%, respectively. This result evidenced that the greatest contribution to the global effect of correlation between VESS and soil properties is provided by BD.

Sucrose accumulation curves represent the maturity profile of sugarcane cultivars, which is considered as a character of interest for the selection of genotypes in breeding programs. However, variations due to the environment (E) and interaction between genotype and environment (G × E) may be confused with the effect of genotype (G) and hinder the selection process of promising clones. The objective of this study was to identify a group of accumulation curves with high intra-group genotypic variability in the sucrose accumulation process throughout several E. This group is then used to select genotypes according to their maturity profile. A protocol is presented whereby the following statistical tools are integrated: (i) classification of nonlinear accumulation curves according to parameters associated with the beginning of the maturity process, sucrose accumulation rate and the time elapsed until the accumulation rate decreases, (ii) estimation of the genotypic contribution to intra-group variability of each accumulation curve parameter within each group and (iii) identification of the group of accumulation curves with the higher contribution of genotypic variability to total variance of sucrose accumulation parameters. The novelty of the work lies in the sequence of analytical steps to identify information useful to select genotypes according to their maturity profile. The protocol involves estimating parameters of nonlinear models for fitting maturity curves in multi-environment trials, clustering of curves according to the sucrose accumulation parameters and estimation of variability due to G, E and G × E within each cluster to identify the group with characteristic genotypic curves. Its implementation is illustrated using 175 sucrose accumulation curves of nine sugarcane clones evaluated in different crop cycles (first and second ratoons) and several environments (7 to 50 for each clone) in Tucumán, Argentina. The proposed protocol allows identifying sucrose accumulation curves that exhibit a high genotypic variance, thus facilitating the selection of the best clones.

Background: Early sexual maturation is a challenging obstacle to overcome in Atlantic salmon farming. This trait primarily affects males and occurs in both freshwater fish farms and sea culture cages during the fattening phase. Current strategies for preventing early maturation include a combination of genetic selection and management practices. However, the genetic architecture of early maturation appears to vary across populations, strains and environments. Our study aimed to elucidate the genetic architecture of early maturation in the Lochy strain of Atlantic salmon using genome-wide SNP panels. This European-origin strain grows rapidly but is prone to high rates of precocious male maturation if not properly managed. Results: We report two genome-wide association (GWAS) results focusing on males of the Lochy strain of Atlantic salmon. The first included seawater-cultured fish (Group-SA: 714 males, 80 precocious and 634 immature) with an artificial continuous light photoperiod, while the second included freshwater-cultured fish (Group-FN: 707 males, 333 precocious and 374 immature) with a natural photoperiod. Group-SA was genotyped using a custom 46,115-SNP Illumina microarray, whereas Group-FN employed a custom 62,044-SNP Thermo microarray. Genomic heritability of early maturation in males was consistently high across models—ranging from 0.62–0.79 in seawater and from 0.54–0.62 in freshwater. In Group-SA, one significant SNP associated with early sexual maturation were identified on chromosome Ssa25. In Group-FN, sixty significant SNPs associated with early sexual maturation were identified on chromosomes Ssa5, Ssa7, and Ssa25. The genetic variance explained by these SNPs ranged from 16.1–53.7%, while the proportion of phenotypic variance explained varied from 8.7% to 29.1%. The identified candidate genes included chmp2b and vgll3 , both previously reported in other domesticated European-origin populations, suggesting some degree of convergence. Conclusions: The SNPs associated with early maturation are promising candidates for application in breeding programs in the Lochy strain aimed at implementing improved control strategies against early maturation in both freshwater and sea environments.