Background: Modern agriculture operates within an increasingly unpredictable environment, influenced by dynamic market fluctuations and environmental variability. Timely and accurate prediction of crop prices is essential to support data-driven decision-making for farmers, policymakers, and stakeholders in the agricultural supply chain. Objective: This study presents a comprehensive machine learning framework aimed at forecasting crop prices by integrating environmental, economic, and logistical variables. The primary objective is to enhance agricultural profitability and sustainability through precise, data-informed insights. Methods: A diverse dataset was compiled, encompassing features such as temperature, precipitation, supply and demand metrics, transportation costs, fertilizer application, pest infestation levels, and market competitiveness. Advanced feature engineering techniques were applied to preprocess and refine the input data. Several machine learning models, including Linear Regression, AdaBoost, Support Vector Machines, Random Forests, and XGBoost, were developed and evaluated for their predictive accuracy. Results: Among the evaluated models, XGBoost outperformed the others by delivering the highest accuracy in price forecasting. Its capability to model complex, non-linear relationships and capture intricate feature interactions proved critical for reliable predictions. The enhanced precision offered by XGBoost enables stakeholders to make informed decisions, contributing to increased profitability and optimized resource allocation. Conclusions: The proposed XGBoost-based crop price prediction framework demonstrates robust performance in real-time agricultural forecasting scenarios. By incorporating a wide range of environmental and market variables, the model significantly reduces uncertainty in the agri-value chain, thereby supporting sustainable farming practices and improving economic resilience.

Abstract
The experiment was conducted at the Department of Animal Science, Livestock Teaching and Research Farm, Usmanu Danfodiyo University, Sokoto, Nigeria. The objective was to evaluate the effects of different modes of vitamin E supplementation on adaptability and stress biomarkers in Uda rams under semi-arid conditions. Twelve yearling Uda rams (18–23 kg BW) were randomly assigned to three treatment groups (n = 4 per group; experimental unit = ram) in a Completely Randomized Design (CRD) with four replications. Vitamin E (DL-α-tocopheryl acetate, Shaanxi Bieyouth Biotech Co. Ltd., China) was supplemented at 40g/kg DM in feed or 40g/L DM in water. The feeding trial lasted for seven weeks (41 days). The basal diet contained 2509 Kcal/kg metabolizable energy, 17.14% crude protein, 19.46% crude fibre, and no additional selenium or carotenoid supplementation.
Feed and water intake were recorded daily. Stress biomarkers (cortisol, prolactin, triiodothyronine [T3], and thyroxine [T4]), antioxidant activity (malondialdehyde [MDA] measured using the TBARS method, superoxide dismutase [SOD] determined with a commercial assay kit, and total antioxidant capacity), and stress indicators (pulse rate, rectal temperature, and respiratory rate) were measured weekly at 8:00 am and 3:00 pm. Data were analyzed using ANOVA under a CRD model, and treatment means were separated using the Least Significant Difference (LSD) test at p < 0.05.

Significant changes were observed in cortisol (55.33, 45.33, 52.66 ng/ml), T4 (8.43, 6.67, 6.57 µg/ml), MDA (2.86, 1.88, 1.89 nmol/ml), and respiratory rate (42.70, 26.00, 31.20 bpm), while other parameters showed no significant differences. Vitamin E supplementation reduced cortisol levels (p < 0.05) when provided in feed, decreased T4 levels when supplemented in water (p < 0.05), and lowered MDA concentrations in both feed and water treatments (p < 0.05), indicating reduced oxidative stress. SOD activity increased when vitamin E was supplemented in water (p < 0.05), whereas prolactin, T3, TAC, pulse rate, and rectal temperature were unaffected.
From these results, we can conclude that Vitamin E supplementation, particularly through feed, effectively reduces stress biomarkers and enhances antioxidant activity in Uda rams, although its effects on thyroid hormones and prolactin require further investigation.
Keywords
Vitamin E; Stress Biomarkers; stress indicators; Antioxidant activity; Uda Ram.
All procedures were conducted in accordance with animal welfare standards and approved by the Department of Animal Science, Faculty of Agricultural Sciences, Usmanu Danfodiyo University Sokoto.

Crop conversion has become an increasingly important strategy for climate adaptation and for overcoming the limitations of traditional farming systems, particularly in low-lying regions. This study, focusing on lotus farming in Thua Thien Hue Province, examines the adoption and impact of lotus as an alternative to rice in flood-prone areas that are at high risk of being abandoned due to low agricultural efficiency. Based on data collected from direct interviews with 101 households in the Phong Dien and Quang Dien districts, this research highlights the critical influence of land-use policies on crop switching. While efforts to promote crop diversification have enabled farmers to transition to alternative crops, restrictive rice land protection policies continue to hinder the expansion of high-value alternatives, such as lotus. This study further explores the adaptive strategies employed by farmers. It analyzes five-year land-use histories to identify ongoing challenges in lotus cultivation, such as vulnerability to erratic weather, pest and disease outbreaks, and high input costs. Despite these obstacles, lotus farming emerges as a viable and economically promising option for marginal lands. These findings underscore the need for changes in land-use policies, increased investment in local lotus varieties, and enhanced agricultural support services to improve the long-term sustainability of lotus and other high-value alternative crops.

Seed dormancy in Adlai (Coix lacryma-jobi) limits its agricultural potential. This underutilized crop has great potential as an alternative source to common carbohydrates such as rice and corn, but it is hampered by this physiological condition. Conventional dormancy-breaking methods often involve synthetic chemicals, which are costly and environmentally detrimental. This study evaluates Black Soldier Fly Frass Tea (BSF FT), an organic alternative rich in nutrients and plant growth regulators (PGRs), as a priming agent for stored Adlai seeds. A completely randomized design (CRD) with eight treatments (including BSF FT at 10–25 mL/L, gibberellic acid (GA₃), and control) was replicated three times. Germination parameters (days to 50% germination, germination rate, seedling vigor, and biomass) and pH effects were analyzed. The results revealed that BSF FT at 20 mL/L significantly improved germination (92%, comparable to GA₃), with a 77.78% germination rate (3.33 days to 50% seed germination and enhanced seedling vigor (shoot: 16.03 cm; root: 16.67 cm)) and biomass of 16.97%, showing great potential as a seed priming agent. Undiluted BSF FT (pH 4.45) inhibited germination, highlighting pH-dependent efficacy. The results signified that BSF FT is a low-cost, eco-friendly alternative to synthetic PGRs, and is optimal at 20 mL/L. Field trials and biochemical analysis of PGRs in BSF FT are recommended for scalability.

The important roles animal foods, particularly pork and chicken, play across the globe cannot be overstated. However, the high cost of feed ingredients and growing concerns about antibiotic resistance are limiting their sustainable production. With these growing concerns, significant research and investment have focused on identifying sustainable and cost-effective alternatives to feed ingredients and antibiotics. Probiotics have emerged as promising candidates for replacing antibiotics in both human health and livestock production. However, their widespread application is limited, owing to an incomplete understanding of their functional mechanisms. In this study, immunogenic peptides derived from probiotic bacterial species, Ligilactobacillus saerimneri (isolated from the cecum of a 20-day-old chicken), Ligilactobacillus salivarius (isolated from the feces of swine) and Lactobacillus acidophilus, were investigated for their ability to induce interleukin-10 (IL-10), interleukin-13 (IL-13), and interferon-gamma (IFN_γ) using a computational approach, based on their essential functions in immune modulation in this preliminary study. Six peptides each were considered from each organism. Their physico-chemical properties were also assessed. Ligilactobacillus salivarius-derived peptides obtained the highest IL-10-inducing capacity, which was statistically similar to Ligilactobacillus saerimneri-derived peptides but significantly (p<0.05) higher than Lactobacillus acidophilus-derived peptides. IL-13-inducing potential was significantly (p<0.05) higher for L. acidophilus-derived peptides when compared with both L. salivarius-derived peptides and L. saerimneri-derived peptides. IFN_γ was statistically not different across the groups. The theoretical isoelectric point ranged between 4.00 and 12.01, indicating their potential to be well-accommodated in the gastrointestinal tract. The instability index ranged between -31.32 and 107.81. Out of the peptides considered, four (22%) are regarded as unstable. The peptides can withstand a varied temperature range, with the aliphatic index being generally high. The GRAVY score ranged between -2.065 and 1.110. 22% of the peptides, and based on their GRAVY scores, most are hydrophobic, while the rest are hydrophilic. These findings reveal a deeper understanding of probiotic immune pathways and highlight their potential for sustainable applications as therapeutic feed additives, functional food supplements, and innovative candidates in vaccine development.

Crop recognition using remote sensing data is vital for modern agriculture, enabling dynamic crop mapping, land use monitoring, and cropland structure analysis. Beyond identifying crops, distinguishing irrigated from rainfed croplands enhances agricultural water management. This study utilized the Normalized Difference Vegetation Index (NDVI), collected monthly from the Kherson and Mykolaiv regions (Ukraine), to classify irrigated and rainfed croplands and crop types via machine learning. NDVI data, sourced from the OneSoil platform, covered grain corn, wheat, sunflower, and soybeans, with equal representation of irrigated and rainfed conditions, forming eight distinct classes. Five algorithms were applied: Linear Discriminant Analysis (LDA), Multiple Logistic Regression (MLR), Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB). Classification was performed on the original dataset, an augmented dataset (via Gaussian noise), and a normalized dataset. Performance was assessed using k-fold cross-validation, with F1 scores computed for each model in Python 3.13 with relevant libraries. The results showed normalization had no impact on performance. All models excelled at separating irrigated from rainfed croplands, with the SVM achieving the highest F1 scores (0.9292 original; 0.9352 augmented) and LDA and MLR the lowest (0.8938 original; 0.8879 augmented, respectively). Crop type recognition proved more challenging, with F1 scores not exceeding 0.60; XGB scored highest on the original dataset (0.5911) and RF on the augmented dataset (0.6346). Two-fold data augmentation generally improved F1 scores, with the SVM performing best overall on the augmented dataset (average F1: 0.7839), while XGB led on the original dataset (0.7556). Data normalization proved ineffective for monthly NDVI-based crop recognition, suggesting it can be omitted. Gaussian noise augmentation enhanced most models’ performance and altered their relative efficacy. The SVM excelled at distinguishing irrigation status, but simultaneous crop type classification remains difficult, warranting further refinement. These findings highlight the potential of applying machine learning with NDVI data for irrigation classification and the need for improved approaches to crop type identification.

Government policies have long sought to make fertilizers accessible to farmers through subsidies, as fertilizers are known to enhance farm output and productivity. In this paper, we attempt to show the extent to which this policy emphasis has influenced the trend and characteristics of past academic studies on fertilizers in Ghana. We reviewed 37 peer-reviewed articles and four policy documents. These documents were collected by using databases, such as ProQuest, Web of Science, and Google Scholar, with the following keywords: fertilizer policy, fertilizer subsidies, agriculture policy, and Ghana. In examining the contents of these past studies and policy documents, we focused on productivity and profitability, income, fertilizer access, food security, and study areas. The results show that about 54% of the articles focused on profitability and productivity. In terms of study areas, about 52% examined northern regions. Our comparison between past studies and policy documents shows that Ghana’s past fertilizer studies closely corresponded with fertilizer policy implementation practices. Subsidies have considerably improved farmers’ access to fertilizers, increased fertilizer application rates, enhanced crop productivity, and contributed to mitigating food insecurity. On the contrary, none of the review looked at environmental impacts of increasing inorganic fertilizer use. Our review highlights the need for incorporating sustainability perspectives into studies on food and agriculture in Ghana.

This study examined the level of awareness and the extent of adoption of improved sorghum varieties among smallholder farmers across five key villages: Malete, Lanwa, Olooru, Elemere, and Arobad in the Moro Local Government Area of Kwara State, Nigeria. A total of 120 respondents were randomly selected, with 24 participants sampled per village. Data collection was conducted using structured questionnaires, and the results were analyzed through descriptive statistics and probit regression to identify the factors influencing adoption behavior.

Findings indicate that 60.9% of the respondents were within the 31–50-year age bracket, while 48.7% were over 50 years. The majority were male (76.7%), married (83.3%), and engaged in full-time farming (75.0%), with a significant proportion (41.7%) having no formal education. Most practiced subsistence agriculture on small plots ranging from 1 to 3 hectares (79.3%), with limited access to financial resources (78.4%).

Although awareness of improved sorghum varieties was relatively high at 75%, actual adoption remained low at 15%. Among those who adopted, early-maturing and dwarf varieties were the most preferred. The principal constraint to adoption was the inadequacy of extension services (50%), while radio served as the primary information source for 33.3% of farmers. Mixed cropping was the dominant farming system, practiced by 50% of the respondents.

Probit regression analysis revealed that education level, access to extension services, and farm size were statistically significant predictors of adoption. This study underscores the need for strengthened agricultural extension systems, enhanced input accessibility, and strategically designed awareness programs particularly targeting young farmers to drive an increased adoption of improved sorghum technologies.

The precise and accurate real-time assessment of raw milk quality during the milking process through a near-infrared spectroscopic sensing system has not been performed, and is potentially hindered by elements likes cow parity. Therefore, this research focused on the influence of cow parity, or the number of times a cow has calved, on the reliability and exactness of a near-infrared (NIR) spectral detection system in assessing three key milk quality indicators: fat content, lactose, and somatic cell count (SCC). This study was conducted with two cows in their second calving phase at the dairy facility of Hokkaido University. We gathered milk absorbance spectra with the NIR system across a wavelength spectrum from 700 to 1050 nm. Milk fat and lactose levels were measured through a MilkoScan device, while SCC measurements were taken with a Fossomatic device. Calibration models were developed using three groups of sample data, including one from the first parity trial, another from the second parity trial, and a combined set from both trials. These calibration models employed partial least square regression analysis, and the accuracy and reliability of these models were subsequently tested. The coefficient of determination and standard error of prediction values obtained for both the first and second parity, alongside the combined data, were comparable for the parameters of milk fat and SCC, with the exception of lactose. Additionally, the first parity data set was utilized for validating the second parity data set, and vice versa. The findings showed that the measurements, particularly for lactose levels, were notably influenced. This indicates that a cow’s parity could affect the precision of NIR sensing systems in evaluating the quality of cow milk during milking sessions.

Agriculture plays a critical role in ensuring food security, supporting livelihoods, and driving economic development. However, it is increasingly threatened by climate change—particularly by extreme weather events such as droughts, floods, and storms. This review explores the complex relationship between agriculture, ecosystems, and the environment, with a specific focus on how these climate extremes impact agricultural productivity, farming sustainability, and the health of natural resources. It examines how agriculture both contributes to climate change through greenhouse gas emissions and suffers from its consequences, including soil degradation, water scarcity, and biodiversity loss. The review also discusses adaptation and mitigation strategies, such as climate-smart agriculture, sustainable land and water management, technological innovations, and policy interventions. Emphasis is placed on the need for integrated efforts involving science, policy, and local communities to build resilient agricultural systems capable of withstanding climate-related shocks. These strategies are essential to protect environmental health and ensure long-term food security in a changing climate.