Early Crop Research Articles

Early Season Crop Acreage Estimation for Pigeon Pea using SAR Data: A Case Study of Kalaburagi District, Karnataka

Crop acreage estimates using space-based observations during mid-season and pre-harvest periods are operationally provided for major Kharif and Rabi crops in India. These are critical inputs for planning and decision-making concerning food security, storage, pricing, and procurement. This work explores the potential of Satellite C-band Synthetic Aperture Radar (SAR) data in VV and VH polarization, acquired during monsoon season, for early crop acreage assessment of Pigeon Pea. The present study evaluates two classification approaches based on multi-temporal SAR data to generate a spatial distribution map of the pigeon pea crop in the Kalaburagi region of Karnataka. The temporal profiles of sigma nought (backscatter coefficient) and Entropy vs. Alpha Angle were studied with reference to crop phenology. Random forest algorithm has been used to classify multi-temporal SAR Ground Range Detected (GRD) data from June to November 2019. Temporal SAR data from June to early November with VV+VH polarization was optimal for tur area assessment with 85% accuracy. This study also examines phase and intensity information from 3-date SAR Single Look Complex (SLC) data with an unsupervised Wishart Classification approach for improved crop acreage estimation. The results emphasize the effectiveness of dual-polarimetric SAR data for timely crop inventory of Pigeon Pea during the Kharif season.

Modelling agricultural landscape complementation for natural pest control

Abstract Pest‐regulating natural enemies often require crop and non‐crop habitats to persist and be effective. These habitats offer hibernation sites, alternative prey or floral resources but can also be complementary in when they provide resources. The relative contribution of these different habitats to the performance of pest‐regulating insects is largely unknown, since it is difficult to study empirically. Landscape‐based population‐dynamical modelling can fill this research gap. In this study, we modelled the dynamics of predatory hoverflies (Diptera: Syrphinae) and their aphid prey in a collection of habitats. These hoverflies are dependent on different habitats for different reasons. While their larvae predate on aphids, adult hoverflies require floral resources. Resources are often segregated in different habitats. In addition, they are only temporarily available in any habitat type. In our model, hoverflies move between different habitats and select where to feed and where to produce off‐spring based on optimal foraging considerations. The model represents habitats common in arable landscapes and their temporal availability of resources is parameterized based on field observations. The model shows that effective pest suppression will only occur in the presence of at least three different habitats, including two crops that provide prey resources at different times of the year. A woody habitat with shrubs and trees provide aphid prey very early and late in the season, whereas an early crop and a late crop cover the period in between. In addition, these habitats need to provide floral resources in the same period as aphids, for example by flower strips in the margins of crop fields or blossoming trees or shrubs in the woody habitat. Under the model assumptions, the best pest suppression is obtained when the woody habitats take up 6% to 10% of the landscape. In addition to yearly population fluctuations, also bi‐ or multi‐yearly cycles may occur, depending on the composition of the landscape. Synthesis and applications. Our model shows when an agricultural landscape is ‘complete’ for natural enemies (and for effective pest control). For this, it needs to contain multiple habitats that supply floral and prey resources in different periods of the year.

Pink bollworm (Pectinophora gossypiella) movement with respect to rosette flowers in cotton: Novel insights for integrated pest management

Aim: This preliminary study aimed to investigate the movement patterns of Pectinophora gossypiella (Saunders) (Lepidoptera: Gelechiidae) larvae in the rosette flowers. Methodology: Field experiments conducted on the migration behavior of pink bollworm larvae with respect to rosette flowers in cotton fields. Observations included monitoring infested flowers, larval stage duration within rosette flowers, and larval movement to soil for pupation, larval mortality post-drop, and larval migration to early bolls, all conducted without insecticide application to reflect natural conditions. Results: The movement of the larvae was tracked and recorded from the start of flowering to the boll formation stage. Nearly, 44.88% of the larvae present on the infested flowers had moved to the soil for pupation, while 14.29% had moved to newly formed bolls on the same rosette flower. Additionally, 30.90% of the larvae had moved to dry leaf debris on the soil, and the remaining 9.93% either escaped or died due to environmental factors such as damp soil. Notably, the study showed that dry soils or light debris accumulation were the most favorable environments for pink bollworm larvae. Interpretation: The present study has generated useful information regarding the movement of PBWs larvae from rosette flowers to bolls that contribute to infestation. Hence, by implementing integrated pest management strategies during the early crop periods between 60 and 100 DAS, green boll infestations can be avoided and economic yields improved. Key words: Larval movement, Pest carryover, Pest management, Rosette flower

Beyond yield: Unveiling farmer perceptions and needs regarding weed management in Bangladesh.

More than 3.5 billion people depend on rice for more than 20% of their daily calories. Globally, Bangladesh is the third largest rice producer. With 171 million people, Bangladesh is also among the top consumers. Local rice production not only affects the country's food security but also influences the global rice trade. A large yield gap has been reported due to weeds. Traditional hand weeding is very costly because of labor shortages resulting from industrialization. Limited data showed a higher yield and profits when using herbicides. However, quantitative data on various aspects of weed management and associated issues representing the country's variable rice ecosystem, which is characterized by 30 agroecological zones, are lacking. We collected data on weed management practices from 865 farmers and 69 agrochemical shops covering all 30 agro-ecological zones (AEZs) through a structured survey. We observed a significant regional variation among various parameters. Approximately 82% of farmers use herbicides, and few rely solely on either manual weeding or herbicides. Pre-emergence herbicides are the predominant. Application procedures are almost the same across the country. Although 40% of farmers had secondary and higher-level education, most depend upon local sellers' suggestions rather than reading the product label regarding the dose. Few farmers consider herbicides hazardous, and respondents rarely perceive any environmental impact. Pyrazosulfuron ethyl (35%) and acetochlor-containing bensulfuron methyl (27%) are the most-used chemical species. Approximately 45% of farmers observed that herbicides suppress early seedling growth. Additional fertilizer is required to compensate for this. Multiple weed species that are difficult to control through presently used herbicides were noted in all AEZs. Around 64% of farmers observed that herbicide application contributes to higher yields as a function of timely weeding. Cost comparisons showed that high labor prices will make rice cropping unprofitable in most parts of the country if herbicides are eliminated. Clear adverse effects of pre-emergence herbicides on early crop growth implied the potential benefits of broad-spectrum herbicide-tolerant genetically engineered (GE) rice to sustain the country's food security. Additionally, such GE rice could incentivize the adoption of alternate wet and dry irrigation methods, leading to water and cost savings.

The potential of seaweed biochar and fly ash amendments in enhancing vermi-degradation and the fertilizer value of cow manure, wastepaper-based vermicompost

This study evaluated the potential of amending cow manure (CM) based vermicompost with fly ash (FA) and seaweed biochar (Bio) on vermidegradation, nutrient release and early crop growth. All treatments, except CM + fly ash, resulted in a C/N ratio below 20, indicating a mature compost. The CM + Biochar treatment had the highest Olsen-P of 274.75 mg/kg whilst the CM + Fly ash treatment had the lowest concentration of 239.13 mg/kg. Only Zn showed a consistent increasing trend of 51.5 %, 45.6 %, 53.6 %, and 47.8 % for the CM + fly ash, CM + FA + Bio, CM + Bio, and CM treatments, respectively. For crop germination, the CM + fly ash compost needs to be substituted at 25 % in cocopeat, whilst 50 % substitution is suitable for seedling development. Future studies need to evaluate the potential of removing salts from seaweed-biochar, and the field soil application of seaweed and fly ash amended vermicomposts.

Growth yield performance of different hybrid cauliflower (Brassica oleraceae var. botrytis L.) cultivars in Dang, Nepal

Cauliflower is commonly grown in terai and mid-hills during the winter season (September to December), thus known as mid-season cole crop in the context of Nepal. As this cropping period possess favorable environmental condition to grow, and the production cost is comparatively lower and productivity is higher as compared to early and late seasons crop. Farmers are cultivating various hybrid (F1) cultivars to increase the yield and income. Every year, several hybrids are being imported in Nepal and there needs a varietal trial before being recommended at farmer’s field. Thus, this experiment was conducted at horticulture farm of Campus of Live Sciences. Tulsipur, Dang, Nepal for two consecutive years (2021 and 2022 AD) to evaluate the growth and yield attributes of five hybrid cauliflower cultivars. Cultivars viz. Snow Best, Snow Crown, Super White Top, Rami and Damy were treated as treatment and replicated four times in Randomized Complete Block Design. The experiment showed that cultivar Super White Top and Snow Crown had desirable vegetative characteristics, better yield, and higher harvest index as compared to other cultivars. Hence, Super White Top and Snow Crown could be promoted for cultivation in the agro climatic zones related to that of Tulsipur, Dang. Considering the economically important growth and yield attributes Super White Top and Snow Crown were found to be the suitable mid-season hybrid cultivars in Dang condition.

Understanding the Significance of Raffinose Family Oligosaccharides in Seed Physiology

Seed vigour and longevity are pivotal agronomic traits with profound implications for crop yield, food security, and the global economy. Seed longevity, often defined by the duration of seed viability, is crucial for effective gene bank management, influencing seed regeneration cycles and ensuring the long-term conservation of plant genetic resources. The inevitable process of seed deterioration, driven by a complex network of biochemical reactions, leads to altered metabolism and damage to critical cellular components such as membranes, DNA, mitochondria, proteins, and the antioxidative defence system. In recent research, Raffinose family oligosaccharides (RFOs) have emerged as key contributors to enhancing seed vigour and longevity. These sugars perform multiple functions in plants, including tolerance to abiotic and biotic stresses, regulation of seed germination, and maintenance of desiccation tolerance, all of which are essential for overall seed health. Studies suggest that RFOs significantly bolster seed vigour and longevity through mechanisms such as cytoplasmic vitrification, water replacement, and osmoprotection in dried seeds. These oligosaccharides are particularly abundant in the seeds of leguminous crops and are also found in roots and specialized storage organs. The glassy state formed by RFOs is vital for protecting cells from oxidative damage caused by reactive oxygen species (ROS), enhancing the stability of enzymes, and preventing deleterious conformational changes in proteins. Furthermore, delaying the degradation of RFOs has been shown to inhibit premature germination, underscoring their critical role in early seedling development and successful crop establishment.

Albedo of crops as a nature-based climate solution to global warming

Abstract Surface albedo can affect the energy budget and subsequently cause localized warming or cooling of the climate. When we convert a substantial portion of lands to agriculture, land surface properties are consequently altered, including albedo. Through crop selection and management, one can increase crop albedo to obtain higher levels of localized cooling effects to mitigate global warming. Still, there is little understanding about how distinctive features of a cropping system may be responsible for elevated albedo and consequently for the cooling potential of cultivated lands. To address this pressing issue, we conducted seasonal measurements of surface reflectivity during five growing seasons on annual crops of corn-soybean–winter wheat (Zea mays L.- Glycine max L. Merrill—Triticum aestivum L.; CSW) rotations at three agronomic intensities, a monoculture of perennial switchgrass, and perennial polycultures of early successional and restored prairie grasslands. We found that crop-species, agronomic intensity, seasonality, and plant phenology had significant effects on albedo. The mean ± SD of albedo was highest in perennial crops of switchgrass (Panicum virgatum; 0.179 ± 0.04), intermediate in early successional crops (0.170 ± 0.04), and lowest in a reduced input corn systems with cover crops (0.154 ± 0.02). The strongest cooling potentials were found in soybean (−0.450 kg CO2e m−2 yr−1) and switchgrass (−0.367 kg CO2e m−2 yr−1), with up to −0.265 kg CO2e m−2 yr−1 of localized climate cooling annually provided by different agroecosystems. We also demonstrated how diverse ecosystems, leaf canopy, and agronomic practices can affect surface reflectivity and provide another potential nature-based solution for reducing global warming at localized scales.

ECONOMIC AND BIOLOGICAL EVALUATION OF RADISH HYBRIDS FOR GROWING IN OPEN SOIL IN THE CONDITIONS OF THE CENTRAL PART OF THE RIGHT BANK FOREST-STEPPE

Radish is an early vegetable crop with a very short growing season, widely cultivated worldwide. At the same time, the extensive varietal resources of radishes and the changing environmental conditions compel agroproducers to perform more careful selection of varieties/hybrids to achieve high yields of marketable products. For this purpose, an agro-biological evaluation of eight radish hybrids of different maturity periods was conducted in open-field cultivation. Differences were found in both the duration of phenophases and the growing period of radish plants. The hybrids Stellar and Rockstar were characterized by faster entry into phenological phases, root formation, and maturation, reaching the technical maturity phase on the 25th day. In terms of biometric indicators at the technical maturity phase (BBCH 49), the hybrid Adele stood out, with plants having the highest height (18 cm), leaf rosette width (18 cm), number of leaves per plant (8 pcs), and area (17.6 thousand m2/ha). Over the years of research from 2017 to 2019, which were marked by contrasting weather conditions, the highest yield was obtained from the Adele hybrid, at 26.1–27.3 t/ha, with a 15% advantage over the control and a yield increase of 3.5 t/ha. The hybrids were ranked by yield as follows: Adele > Eliza > Stellar > Rockstar > Rosetta > Roxanne > Donar > Rolex. The highest quality indicators were found in the root crops of the Adele, Stellar, and Rockstar hybrids. Based on the visual assessment of radish root crops, analysis of their linear dimensions, and quality indicators, the hybrids were ranked as follows: Adele > Stellar > Rockstar > Eliza > Rosetta > Roxanne > Donar > Rolex. A strong direct correlation was found between yield and root weight (r=1), as well as between the developmental phases of the plants (seedling emergence, appearance of the first true leaf, growth and development of leaves and roots) and the technical maturity of the root crops (r=0.90–1.00). The number of leaves per plant correlated with plant height (0.97) and the developmental phases of the plants (0.91–0.97). The sugar content in the root crop correlated with the dry matter content and the root diameter (0.92). Based on the agro-biological evaluation of radish hybrids of different maturity groups, it was determined that the most productive hybrids with quality root crops for open-field cultivation are the early-maturing Stellar, the mid-maturing Eliza, and the late-maturing Adele, which are recommended for cultivation in farms of various ownership forms in the central part of the Right-Bank Forest-Steppe.

Seed priming with potassium nitrate alleviates the high temperature stress by modulating growth and antioxidant potential in carrot seeds and seedlings

Early season carrot (Daucus carota) production is being practiced in Punjab, Pakistan to meet the market demand but high temperature hampers the seed germination and seedling establishment which cause marked yield reduction. Seed priming with potassium nitrate breaks the seed dormancy and improves the seed germination and seedling growth potential but effects vary among the species and ecological conditions. The mechanism of KNO3 priming in high temperature stress tolerance is poorly understood yet. Thus, present study aimed to evaluate high temperature stress tolerance potential of carrot seeds primed with potassium nitrate and impacts on growth, physiological, and antioxidant defense systems. Carrot seeds of a local cultivar (T-29) were primed with various concentration of KNO3 (T0: unprimed (negative control), T1: hydroprimed (positive control), T2: 50 mM, T3:100mM, T4: 150 mM, T5: 200 mM, T6: 250 mM and T7: 300 mM) for 12 h each in darkness at 20 ± 2℃. Seed priming with 50 mM of KNO3 significantly enhanced the seed germination (36%), seedling growth (28%) with maximum seedling vigor (55%) and also exhibited 16.75% more carrot root biomass under high temperature stress as compared to respective control. Moreover, enzymatic activities including peroxidase, catalase, superoxidase dismutase, total phenolic contents, total antioxidants contents and physiological responses of plants were also improved in response to seed priming under high temperature stress. By increasing the level of KNO3, seed germination, growth and root biomass were reduced. These findings suggest that seed priming with 50 mM of KNO3 can be an effective strategy to improve germination, growth and yield of carrot cultivar (T-29) under high temperature stress in early cropping. This study also proposes that KNO3 may induces the stress memory by heritable modulations in chromosomal structure and methylation and acetylation of histones that may upregulate the hormonal and antioxidant activities to enhance the stress tolerance in plants.

Using an Uptake Enhancer to Mitigate Nitrogen Leaching While Enhancing Uptake Efficiency

Nitrogen (N) has the most crucial influence on raising agricultural productivity of all other plant nutrients given to crops. However, 50% of the N given to crops is dissipated to the environment globally, resulting in environmental concerns due to leaching. Current research shows that intensive agricultural production systems, which are still used in a large proportion around the world, are prone to N loss. This study aimed to investigate the effect of uptake enhancer applications on N movement in the soil profile based on 10 cm depth intervals, as well as its effects on N uptake and vegetative growth of oats at 4-week intervals over a 16-week period, using sandy soil as a growing medium. Oats were cultivated in a glasshouse setting in polyvinyl chloride (PVC) columns of 60 cm in height. Six treatments were employed at the 3rd leaf growth stage, and each was replicated four times. The experiment had a constructive and a destructive part, which was employed to monitor crop N uptake at four growth stages. Analyses of soil and plant samples were carried out in all the growth stages. The treatments containing the uptake enhancer prevented N from leaching, particularly at the top 20 cm soil depth, with impressive reductions of 194% at 0–10 cm depth and 186% at 10–20 cm depth, during the first 4 weeks after planting. The uptake enhancer also promoted early vegetative growth and crop performance with 15%. In conclusion, the study revealed that employing the uptake enhancer can improve the efficacy of N fertilizer, thereby reducing the application rate of the fertilizer in agroecosystems.

Plant genotype and inoculation with indigenous arbuscular mycorrhizal (AM) fungi modulate wheat productivity and quality of processed products through changes in the frequency of root AM fungal taxa

ContextArbuscular mycorrhizal fungi (AMF) have been extensively applied as biofertilizers in wheat to promote crop productivity. However, variability in AM root colonization, grain yield, and nutrients was observed among wheat genotypes and according to AM genotype and environment. ObjectivesWe hypothesized that wheat response to AM inoculation is more affected by genotype than environment; the response is driven by increases in AM abundance and community structure changes, and not by modification of composition. MethodsWe inoculated an indigenous AM consortium on four old genotypes (Bianco Nostrale, Andriolo, Abbondanza, Sieve) and one modern variety (Bologna) of bread wheat for two years. The effect was evaluated by assessing grain yield, nutrients, and quality of processed products (flour and breadsticks), while the AM abundance and the community composition and structure in roots were characterized, at two plant growth stages, using morphological and molecular tools. ResultsThe functional traits of AMF and plant were better explained by inoculation than by genotype or environment (33 %, 17 %, 4 % of total explained variance), although significant interactions environment x genotype and genotype x inoculation were highlighted. Consistent increases in AM abundance in Sieve and Bologna were associated with positive changes in grain yield and nutrients, supporting the good responsiveness of these genotypes with inoculated AMF, while the plant response of other genotypes was shaped by air temperature and rainfall. However, we did not find significant correlations between changes in AM colonization and mycorrhizal response ratio, with the exception of P and K. After inoculation, AM community composition was similar in all wheat genotypes, but the structure greatly differed among genotypes in interaction with inoculation and plant growth stage. These changes were significantly related to wheat productivity. A Septoglomus taxon, present in the inoculum, was the best predictor of wheat performance. The characterization of the community structure at early crop development and maturity allowed the identification of fast and latest active AM colonizers. Our results showed for the first time that AM inoculation affect the rheological parameters and nutraceuticals of processed products, although the response was modulated by genotype. ConclusionsThe selection of responsive wheat genotypes is fundamental for the positive outcome of inoculation. The positive effects on wheat productivity and field persistence of the inoculated AMF support the use of indigenous consortia that have low impacts on resident AMF. SignificanceOur findings advance the understanding of the facilitative mechanisms that underlie compatibility between AMF and wheat genotypes.

Early detection of Botrytis cinerea symptoms using deep learning multi-spectral image segmentation

Botrytis cinerea is an airborne plant pathogen that causes grey mould disease on horticultural crops, such as tomato, cucumber, pepper, and more. Early detection is crucial for timely and effective strategies for crop loss prevention. In this study, in planta assays were set up enabling a thorough assessment of grey mould progress on cucumber plants both artificially inoculated with two different inoculation methods, and naturally infected throughout the whole growing season of the host under controlled conditions simulating the environment typically prevailing in greenhouses. Multi-spectral imaging was used to capture a novel dataset across various spectral bands containing multiple stages of infection. Deep learning (DL) segmentation architectures, combined with Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) encoders, were employed to identify B. cinerea at various infection stages. The U-Net++ model with a MobileViT-S encoder performed best, achieving a Dice Coefficient (DC) of 0.677, an Intersection over Union (IoU) of 0.656, and a recall rate of 0.807, with a high overall accuracy of 90.1 %. In regards to early detection, the model achieves an IoU of 0.375 on 2nd day post inoculation (dpi), 0.230 on 1st dpi and 0.437 on the 6th dpi. The infection stages were compared to similar visible symptoms of physiological decline or plant responses to abiotic stress. The outcomes of this study demonstrate an important advance in the Artificial Intelligence (AI) plant health detection, for early crop disease diagnosis.

Enhancing Agricultural Sustainability: Automated Crop Disease Detection through Image Processing Techniques

Abstract: The increasing demand for sustainable and high- yielding agricultural practices has driven the need for advanced technologies in crop disease detection. This paper presents a novel approach to automated crop disease detection utilizing stateof-the-art image processing techniques. In the image acquisition phase, high-resolution images of crops are captured using modern imaging devices. These images are then subjected to preprocessing techniques, including resizing, normalization, and filtering, to enhance their quality. Feature extraction follows, where relevant information is derived from the preprocessed images using advanced image processing algorithms, such as texture analysis and color-based feature extraction. The heart of the proposed system lies in the classification phase, where a machine learning or deep learning model is trained on a curated dataset comprising labeled examples of healthy and diseased crops. The integration of this automated crop disease detection system with existing agricultural frameworks provides real-time or periodic monitoring capabilities. This integration empowers farmers with timely and precise information, enabling early intervention and targeted treatment strategies to minimize crop losses. This research contributes to the ongoing efforts in sustainable agriculture by providing a reliable and efficient solution for early crop disease detection.

Cross Domain Early Crop Mapping with Label Spaces Discrepancies using MultiCropGAN

Abstract. Mapping target crops before the harvest season for regions lacking crop-specific ground truth is critical for global food security. Utilizing multispectral remote sensing and domain adaptation methods, prior studies strive to produce precise crop maps in these regions (target domain) with the help of the crop-specific labelled remote sensing data from the source regions (source domain). However, existing approaches assume identical label spaces across those domains, a challenge often unmet in reality, necessitating a more adaptable solution. This paper introduces the Multiple Crop Mapping Generative Adversarial Neural Network (MultiCropGAN) model, comprising a generator, discriminator, and classifier. The generator transforms target domain data into the source domain, employing identity losses to retain the characteristics of the target data. The discriminator aims to distinguish them and shares the structure and weights with the classifier, which locates crops in the target domain using the generator’s output. This model’s novel capability lies in locating target crops within the target domain, overcoming differences in crop type label spaces between the target and source domains. In experiments, MultiCropGAN is benchmarked against various baseline methods. Notably, when facing differing label spaces, MultiCropGAN significantly outperforms other baseline methods. The Overall Accuracy is improved by about 10%.

Growth and Yield of Summer Squash (Cucurbita pepo L.) as Influenced by Different Coloured Plastic Mulches in the Tarai Region of Uttarakhand

Summer squash is a short-duration vegetable crop with off-season nature and high economic returns per unit area. However, the early crop growth season encounters a number of abiotic stresses like low temperature and frost, which adversely affect the marketable yield and quality of the fruits. This dependency on natural factors restricts the scope of its profitable cultivation, thereby making it necessary to bring more area under protected cultivation. Coloured plastic mulches are an important component of protected cultivation, which are designed to modify the microclimate at the plant and soil levels so as to increase crop production and productivity, as well as quality of the produce, to meet the demands of the consumers. Keeping these considerations in view, the present field investigation was conducted at the Vegetable Research Centre of G. B. Pant University of Agriculture and Technology, Pantnagar (Uttarakhand) during the rabi season of 2019-20 to study the effect of different coloured plastic mulches on the growth and yield of summer squash (Cucurbita pepo L.). The experiment comprised nine treatments (bi-coloured plastic mulches) replicated thrice in a randomised block design. Results revealed that use of different coloured plastic films significantly influenced the growth and yield parameters of summer squash. Red coloured plastic mulch (V1) recorded the maximum values for fruit length (30.78 cm), fruit yield plant-1 (1975.8 g), fruit yield plot-1 (39.51 kg) and total marketable fruit yield (365.52 q ha-1), while biodegradable film of silver-black colour (V7) and black plastic mulch (V4) recorded the maximum plant height (cm) and plant spread (cm), respectively. The maximum diameter of the fruit (110.13 mm) was recorded under black coloured plastic mulch. Considering the prevalent climatic conditions of the tarai region of Uttarakhand, red coloured plastic mulch can be recommended for commercial cultivation of summer squash for obtaining higher fruit yields.

Early-Season Crop Classification Based on Local Window Attention Transformer with Time-Series RCM and Sentinel-1

Crop classification is indispensable for agricultural monitoring and food security, but early-season mapping has remained challenging. Synthetic aperture radar (SAR), such as RADARSAT Constellation Mission (RCM) and Sentinel-1, can meet higher requirements on the reliability of satellite data acquisition with all-weather and all-day imaging capability to supply dense observations in the early crop season. This study applied the local window attention transformer (LWAT) to time-series SAR data, including RCM and Sentinel-1, for early-season crop classification. The performance of this integration was evaluated over crop-dominated regions (corn, soybean and wheat) in southwest Ontario, Canada. Comparative analyses against several machine learning and deep learning methods revealed the superiority of the LWAT, achieving an impressive F1-score of 97.96% and a Kappa coefficient of 97.08% for the northern crop region and F1-scores of 98.07% and 97.02% for the southern crop region when leveraging time-series data from RCM and Sentinel-1, respectively. Additionally, by the incremental procedure, the evolution of accuracy determined by RCM and Sentinel-1 was analyzed, which demonstrated that RCM performed better at the beginning of the season and could achieve comparable accuracy to that achieved by utilizing both datasets. Moreover, the beginning of stem elongation of corn was identified as a crucial phenological stage to acquire acceptable crop maps in the early season. This study explores the potential of RCM to provide reliable prior information early enough to assist with in-season production forecasting and decision making.

Estimating Cotton Yield in the Brazilian Cerrado Using Linear Regression Models from MODIS Vegetation Index Time Series

Satellite remote sensing data expedite crop yield estimation, offering valuable insights for farmers’ decision making. Recent forecasting methods, particularly those utilizing machine learning algorithms like Random Forest and Artificial Neural Networks, show promise. However, challenges such as validation performances, large volume of data, and the inherent complexity and inexplicability of these models hinder their widespread adoption. This paper presents a simpler approach, employing linear regression models fitted from vegetation indices (VIs) extracted from MODIS sensor data on the Terra and Aqua satellites. The aim is to forecast cotton yields in key areas of the Brazilian Cerrado. Using data from 281 commercial production plots, models were trained (167 plots) and tested (114 plots), relating seed cotton yield to nine commonly used VIs averaged over 15-day intervals. Among the evaluated VIs, Enhanced Vegetation Index (EVI) and Triangular Vegetation Index (TVI) exhibited the lowest root mean square errors (RMSE) and the highest determination coefficients (R2). Optimal periods for in-season yield prediction fell between 90 and 105 to 135 and 150 days after sowing (DAS), corresponding to key phenological phases such as boll development, open boll, and fiber maturation, with the lowest RMSE of about 750 kg ha−1 and R2 of 0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time series) for EVI and TVI, which occurred around 80–90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps, and their respective VIs.

Mulching effects on soil evaporation, crop evapotranspiration and crop coefficients: a review aimed at improved irrigation management

AbstractMulching is a widely adopted agronomic practice, often used as a water-saving strategy due to its effectiveness in reducing soil evaporation. However, effects vary depending on the materials used and the extent of mulch soil coverage. Consequently, the impacts of mulching may differ considerably across production systems, preventing the establishment of reliable guidelines for irrigation water management. The objective of this study is to comprehensively review existing literature that compares mulching versus no-mulching management, aiming to gain a deeper understanding of the effects of mulching on soil evaporation (Es), crop coefficients (Kc), and actual crop evapotranspiration (ETc act). 58 studies were selected. The impact of mulching was particularly notable in the early crop stages, when the soil is not fully covered. Data in literature shows that plastic films were more effective in reducing Kc than organic materials. However, this effect, while evident during the early crop stages, diminished throughout the rest of the season. Black plastic films were more effective during the early crop stages compared to other colored plastics, particularly relative to the decrease of Kc, but this effect also diminishes during the rest of the season. Building upon these findings, the study provides guidelines for expected reductions in Kc values based on the type of crop, crop stage, and the mulching material most used in each cropping system.

Machine Learning Algorithms for Early Detection of Legume Crop Disease

Background: Legume crops are an essential component of global agriculture and are widely supplied for human consumption, livestock feed and soil improvement due to their vital nutritional nature. The economic and nutritional significance of legumes is threatened by a multitude of diseases that can cause substantial yield losses. Traditional methods for disease detection, relying on visual inspection, are often subjective and inefficient, leading to delayed intervention. Methods: This study investigates the utilization of machine learning algorithms for the early identification of diseases affecting legume crops. A comprehensive evaluation is conducted on machine learning algorithms, namely Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) with respect to the domain of disease detection. Through a comparative analysis of their performance across different environmental conditions and phases of crop development, this study also explores their strengths and weaknesses. Result: The findings and comparative examination offered significant perspectives on the potential of machine learning algorithms in the realm of early legume crop disease detection. In addition to enhancing crop health and disease management, the research provides support for sustainable agricultural practices and possesses the capacity to augment environmental sustainability and food security through the application of machine learning techniques.