Climate change is turning Bangladesh’s lifeblood—its irrigation water—into a growing menace. Rising sea levels are pushing salt into freshwater supplies, unpredictable rainfall is throwing availability into chaos, and pollution is contaminating essential resources. This study highlights how these shifts are deteriorating water quality, harming soil health, and drastically reducing crop yields, which threaten food security.

From coastal farms grappling with salinity to drought-stricken areas facing dwindling groundwater, the crisis is worsening. Yet, there are solutions: salt-tolerant crops, precision irrigation, and rainwater harvesting bring a glimmer of hope. We urgently need policy reforms, farmer education, and improved infrastructure to tackle this hidden emergency.

Drawing on the latest research, this paper raises the alarm about Bangladesh’s water crisis—and outlines a way forward before it is too late.

Shade projection of crops in vertical towers significantly affects yield productivity and quality. Inside a greenhouse, plants at lower positions receive less radiation than those at higher levels. This uneven distribution of light results in higher and faster growth in plants located at higher levels than at lower ones. Stepwise harvesting can offer a simple and practical solution to improve the viability of vertical systems under low-tech greenhouses in urban and peri-urban areas. However, determining the optimal time for harvest at each crop level requires using predictive crop modelling tools. This study aimed to develop a growth model for vertical hydroponic crops under greenhouse conditions, which estimates the variation in dry biomass accumulation plant positions along the tower. The model is based on Heuvelink's radiation-driven growth equation. Dry matter production is a function of radiation use efficiency (RUE), leaf area index (LAI), extinction coefficient (k), and incident photosynthetically active radiation (PAR). Each vertical tower was a closed system with a 20L lower tank and a 1.6 m high vertical pipe, with 45 holes for plants at 25 plants·m² of density. For model validation, Swiss chard (Beta vulgaris L. 'Ford Hook Giant') was grown in autumn 2024 with Steiner's nutrient solution in vertical towers inside a tunnel greenhouse. Radiation was measured daily at three levels of the canopy, upper (U), middle (M), and lower (L) using a lux meter. The extinction coefficients for each position were estimated using nonlinear GRG optimization, from the Excel® Solver tool. The results show an extinction coefficient between 0.06 and 0.09, which decreased as plant position increased in height. The RUE ranged from 1.12 to 1.79 g·MJ^-1, with the U level being the most efficient. Since R² ranged from 0.88 to 0.95, this indicates that the proposed model shows a good predictive capacity throughout the canopy and could be applicable for scheduling staggered harvests in vertical systems within a greenhouse. Defining the commercial weights of desirable plants, the optimal time of harvest at each level of the tower can be easily predicted.

A field trial was conducted at Horticulture Research Institute, in Marondera Zimbabwe, to investigate the effect of vermicompost (as a basal fertiliser) and vermifoliar (as a top dressing) on bell pepper (Capsicum annum cv. California wonder). The experiment was set up as a Randomized Complete block design (RCBD) with three replications and six treatments: (1) no fertiliser applied (negative control) ; (2) 20g vermicompost and 3 weekly sprays of 50mg vemifoliar; (3) 30g vermicompost and 3 weekly sprays of 50mg vermifoliar ; (4) 40g Vermicompost and 3 weekly sprays of 50mg vermifoliar; (5) 50g vermicompost and 3 weekly sprays of 50mg vemifoliar ; (6) 20g compound C and 10g ammonium nitrate (positive control). The objective of the study was to evaluate the potential of using vermicompost as a sole nutrient source for pepper production and to determine optimal application rates that can be recommend to smallholder farmers in Zimbabwe. Data was collected on plant growth, yield and fruit quality parameters. Significant differences (P ≤ 0.05) were observed across all treatments. The positive control, 20g compound C basal fertiliser application and 10g ammonium nitrate as top dressing recorded the highest performance in all the measured parameters. However, increasing rates of vermicompost (from 20g to 50g/plant) resulted in a positive dose response, with improvements in the marketable fruit number, average fruit weight, average fruit diameter, marketable yield and total yield. Notably, 50g vermicompost treatment was the second-best performer and demonstrated potential as an organic alternative for nutrient management in pepper production. The findings from the study suggest that vermicompost can partially substitute chemical fertilisers, particularly at higher application rate and can be recommended as a viable option for smallholder farmers.

Introduction: Wheat (Triticum aestivum L.) is a critical mass crop that is produced in many countries in different regions. However, this benefit is being countered by the effects of high-temperature stress that become more problematic, especially in late-sown conditions. These high temperatures can significantly impact the phenology, growth patterns, and overall yield of various wheat varieties. Understanding how different cultivars respond to these stresses is essential for developing strategies to enhance resilience and ensure food security in the face of climate change. Late seeding in Bangladesh habitually results in wheat exposure to high temperatures during the significant stages of growth and hence interferes with phenology, growth patterns, and yield constituents. The current study hence, aims at explaining the effects of late sowing-induced heat stress on three high-yielding wheat varieties with the intention of determining those genotypes that have increased thermotolerance to enable long-term wheat production in hot climatic conditions.

Methods: An experiment was conducted during the 2020–21 wheat growing season at the Bangladesh Wheat and Maize Research Institute in Dinajpur, Bangladesh. An experimental split-plot design was implemented, incorporating two planting dates—optimal (25 November) and late (5 January)—and three wheat varieties: BARI Gom 21, BARI Gom 26, and BARI Gom 27. Sowing dates were designated as primary plots, while specific cultivars were utilized as secondary plots. Key characteristics, including phenological stages, leaf area index (LAI), plant height, tillers per square meter, spikelets per spike, grains per spike, 1000-grain weight, biomass, harvest index, and grain yield, were quantified and analyzed by variance analysis.

Results: Delayed seeding considerably accelerated phenological development, leading to a shortened interval to phenological maturity and adversely affecting growth and yield. The optimal sowing date of 25 November yielded superior values for tiller density, leaf area index, plant height, spikelets per spike, grains per spike, 1000-grain weight, biomass, and grain yield compared to subsequent sowing dates. BARI Gom 21 exhibited the highest yield among the types, producing 9900 kg ha⁻¹ under optimal sowing conditions and 7424 kg ha⁻¹ with delayed planting. The second-highest yields were recorded for BARI Gom 26 and BARI Gom 27. The interaction between planting dates and varieties had an impact on yield components, with BARI Gom 21 consistently exhibiting superior performance compared to other types in both scenarios.

Conclusions: It has been empirically proven that the date of wheat planting on 25 November in Bangladesh hastens phenological development, enhances vegetative biomass, and augments yields. BARI Gom 21, with its strong heat tolerance and high-yielding capacity, also represents one that can be selected and grown either under optimal or under late-sown conditions. These findings reaffirm the importance of the inclusion of this diversity in breeding programs aimed at generating heat-tolerant wheat lines and, in that way, strengthening the climate resilience of the national wheat production systems.

The objective of this study is to determine the main drivers of adoption of Climate Smart Agriculture (CSA) practices by smallholders, focusing on six important practices: row planting, crop rotation, improved maize (climate-adapted varieties), agroforestry, soil and water conservation, and crop residue management. For this purpose, this study uses the simple random sampling procedure of survey design for collecting cross-sectional data of 400 farming households in the char lands of Rangpur district. The paper applies descriptive statistics and chi-square test together with multivariate logit (MVL) modeling to account for socio-economic and institutional factors influencing adoption behavior. The results showed that the level of education, farm size, access to extension services, credit availability, and membership in a cooperative significantly increase the probability of adopting all CSA practices. Other environmental factors such as plot inclination or soil fertility also affect adoption in different ways. The research highlights the importance of institutional and resource support in addressing obstacles to the uptake of CSA. Informed by these findings, policy recommendations for integrated extension programs, enhancing access to financial services, and the development of farmer cooperatives are provided as a means to promote sustainable agricultural transformation and climate resilience of smallholder farmers.

A field experiment was conducted to assess the impact of climate change on tomato growth and productivity using the DSSAT model. The results obtained from the field trial were used to calibrate and validate the dynamic crop simulation model DSSAT-CROPGRO for predicting the growth and yield of the tomato crop. The past 30 years of weather data were used to assess the impact of climate variability on tomato productivity. The future climate data generated through a statistical downscaling approach were used to project the impact of climate change on tomato productivity. The experiment was laid out in a Factorial Randomized Block Design (FRBD). The treatments consisted of four planting dates from November 1st to December 15th at biweekly intervals and three nitrogen (N) levels, viz., the Recommended Dose of Nitrogen (RDN), 75% RDN, and 125% RDN. In the future, tomato productivity is expected to decline from the current yield levels due to climate change under hot dry conditions of 20.29 and 26.24 under RCP 4.5 and RCP 8.5 scenarios by the end of the century. Impacts of future climate change could be reduced by altering the planting date from December 1st to October 1st during rabi under RCP 8.5. Though an earlier date of sowing and supplemental fertilizer application had considerable gains in fruit yield under both current and future climate conditions, their magnitude diminished considerably under future climate conditions.

Artificial Intelligence (AI) is rapidly transforming agriculture, offering advanced solutions to the long-standing challenges of climate variability, resource optimization, and food insecurity. However, in many parts of the Global South, particularly South Asia and Sub-Saharan Africa, the adoption of AI in climate-smart agriculture (CSA) remains in its infancy due to infrastructure, policy, and capacity barriers. This study develops a comprehensive roadmap for integrating AI into CSA decision systems in data-scarce and climate-vulnerable regions. This roadmap is formulated through a systematic meta-synthesis of over 200 peer-reviewed articles, FAO and World Bank reports, and real-world case studies of AI applications in agriculture. AI models, including machine learning, deep learning, and geospatial decision support systems, are critically analyzed in terms of their current utilization for yield forecasting, pest detection, early warnings of drought, precision irrigation, and digital farm advisory platforms. A technology–policy–capacity framework is proposed, illustrating how scalable AI tools can be embedded within national agricultural extension systems and local farmer knowledge networks. Therefore, the key findings highlight the potential of open-access satellite datasets (e.g., NASA POWER, Copernicus), federated learning for data privacy in rural areas, and low-power AI devices suited to resource-constrained environments. Ethical concerns such as algorithmic bias, digital exclusion, and governance vacuums are also addressed, with mitigation strategies proposed to ensure equitable AI deployment. This conceptual contribution offers a forward-looking strategy for aligning AI innovation with CSA goals, enhancing agricultural productivity, sustainability, and resilience. The proposed roadmap serves as a practical guide for researchers, policymakers, and agri-tech innovators committed to transforming agri-food systems across the Global South.

Rainfed agriculture is complex and more challenging due to rainfall variability, shrinking land, soil fertility depletion, decreasing carbon (C) stock and reduced system productivity. Alfisols occupy 30% of arable land in semi-arid dryland regions with only 30-40% land use efficiency due to the prevalence of monocropping. Double cropping with efficient rainwater management can increase productivity and stability in rainfed areas by improving crop diversification, nutrient cycling and water use efficiency. The field experiment was conducted at the Gungal Research Farm of ICAR- Central Research Institute for Dryland Agriculture (17^o05’ N, 78^o39’E) between 2022-2023 and 2023-2024 to determine the best possible double cropping system in a rainfed region of Alfisols. The treatments comprising of six legume–oilseed cropping systems with and without rainwater management were laid out in Randomized Block Design with three replications. During the kharif season legumes viz., cowpea, green gram and black gram were sown, and after harvesting of legume crops, oilseeds viz., sesame and safflower were sown in the month of October in both the years. Various crops grown with different rain water management practices demonstrated significant variation in crop growth parameters, such as in kharif, where cowpea recorded the highest biomass (16.21 g plant^-1 and 12.35 g plant^-1) and leaf area index (LAI) (1.58 and 1.52) at 45 DAS in 2022 and 2023, respectively. While in the rabi season, sesame with rainwater management showed the highest growth in terms of biomass (8.14 g plant^-1 and 8.21 g plant^-1) and LAI (0.76 and 0.52) at 45 DAS in both years, respectively. In terms of yield, the cowpea–sesame system with rainwater management achieved the highest black gram equivalent yield (BGEY) across two years with an average yield of 1758 kg ha^-1. The cowpea–sesame system, with rainwater management, achieved the highest BGEY (1,758 kg ha⁻¹) over two years. Cowpea's deep roots improved soil structure and moisture retention, benefiting the following crop. Sesame’s drought tolerance, shorter duration, and higher market value further enhanced yield. This system proved the most efficient pulse legume double-cropping option for rainfed Alfisols. Adopting effective rainwater management practices was found to be beneficial in identifying new double-cropping systems for rainfed region of Alfisols.

Introduction: Data-augmentation algorithms play a crucial role in mitigating the issue of limited training samples in deep learning applications across various agriculture domains. These algorithms are commonly employed by researchers to enhance performance in computer vision tasks. However, with the fast-paced evolution of these methods, the traditional classification, which separates them into classical techniques and generative methods, is now insufficient as it fails to include several important approaches. Furthermore, the abundance of available algorithms makes it difficult to select the most appropriate one for a specific application.
Methods: To address this challenge, this paper proposes a new classification system for image data-augmentation algorithms based on their strategic approaches: matrix transformation techniques, feature expansion methods, and neural network-based generation models.
Results: The study explores the key principles, performance, application contexts, current research trends, and future challenges for each category while offering insights into the future development of data augmentation techniques.
Conclusions: This work provides a useful academic resource for the application of data-augmentation algorithms, particularly in the field of precision livestock farming.

Abstract

Introduction:

Climate change has become a major threat to agricultural sustainability, particularly to drought-prone areas. This paper investigates the adoption of climate-smart agriculture (CSA) technology by smallholder farmers in the Ramanathapuram District of Tamil Nadu and its impact on crop productivity, specifically on paddy cultivation.

Methods:

Data were collected from 180 farm households in 15 villages through structured interviews. Logistic regression and propensity score matching (PSM) methods were used to confirm the influence of socioeconomic factors on adoption of CSA and to assess its impact on yield outcomes.

Results:

The logistic regression results indicated that gender, education, longer experience in farming, the size of farmland, and information from extension services were determinants of CSA practice adoption. Specifically, being a male farmer and having higher school education, farming experience, and access to extension services had a significant positive effect of CSA adoption, and farm size had a negative effect on CSA adoption. In addition, PSM analysis indicated that CSA adaptation led to a significant increase in crop yield. Both matching and linear regression models show that the coefficient of CSA practices on log yield is positive and significant. The R2 value of 0.87 in linear regression model suggests that the model describes a high variation inthe yield.

Conclusions:

These results highlight the role of CSA in improving the resilience and productivity of agriculture in climate-exposed areas. Accordingly, policy interventions should aim at enhancing farmers' education, reinforcing extension, and providing support to smallholders.