Crop Yield Variability Research Articles

Cross-Validation Strategy Impacts the Performance and Interpretation of Machine Learning Models

Abstract Machine learning algorithms are able to capture complex, nonlinear, interacting relationships and are increasingly used to predict agricultural yield variability at regional and national scales. Using explainable artificial intelligence (XAI) methods applied to such algorithms may enable better scientific understanding of drivers of yield variability. However, XAI methods may provide misleading results when applied to spatiotemporal correlated datasets. In this study, machine learning models are trained to predict simulated crop yield from climate indices, and the impact of cross-validation strategy on the interpretation and performance of the resulting models is assessed. Using data from a process-based crop model allows us to then comment on the plausibility of the “explanations” provided by XAI methods. Our results show that the choice of evaluation strategy has an impact on (i) interpretations of the model and (ii) model skill on held-out years and regions, after the evaluation strategy is used for hyperparameter tuning and feature selection. We find that use of a cross-validation strategy based on clustering in feature space achieves the most plausible interpretations as well as the best model performance on held-out years and regions. Our results provide the first steps toward identifying domain-specific “best practices” for the use of XAI tools on spatiotemporal agricultural or climatic data. Significance Statement “Explainable” or “interpretable” machine learning (XAI) methods have been increasingly used in scientific research to study complex relationships between climatic and biogeoscientific variables (such as crop yield). However, these methods can return contradictory, implausible, or ambiguous results. In this study, we train machine learning models to predict maize yield anomalies and vary the model evaluation method used. We find that the evaluation (cross validation) method used has an effect on model interpretation results and on the skill of resulting models in held-out years and regions. These results have implications for the methodological design of studies that aim to use XAI tools to identify drivers of, for example, crop yield variability.

ВЛИЯНИЕ АГРОМЕТЕОРОЛОГИЧЕСКИХ ФАКТОРОВ НА ПРОДУКТИВНОСТЬ ЗЕРНОВЫХ КУЛЬТУР ПО МУНИЦИПАЛЬНЫМ РАЙОНАМ САРАТОВСКОЙ ОБЛАСТИ

The paper presents the results of studying the influence of modern agrometeorological conditions on the yield of different groups of grain crops in the municipal districts of the Saratov oblast. The climatic trends of the recent two decades are analyzed for five weather stations (Khvalynsk, Balashov, Saratov, Ershov, and Aleksandrov Gai). For the Saratov weather station, a longer period (1941-2022) is analyzed. There is an increase in the heat availability and aridity of the territory. The analysis of the dynamics of the crop yield distribution and variability has shown that the most favorable conditions of crop cultivation are formed in the Balashov municipal district. Operational forecast models of the maximum and minimum productivity of winter wheat are developed, which makes it possible to predict a yield with a monthly lead time.

Pattern of Agricultural Progress in India’s North-East and the Contributing Factors: An Econometric Analysis

Despite being blessed with rich agro-climatic conditions, the largest agrarian state in India’s North-East, Assam recorded relatively poor agricultural growth, since independence. The question of agricultural performance in terms of use of factors and growth pattern always arise that seems to vary in different stages of policy shift. Agricultural diversity increased in the initial phase with the expansion of agricultural area but slowed down in the later stages. However, the nature of agricultural diversity and use of resources including land allocations reflects the adaptation of farming community, absorption of labour force and sustainability of earning of farmers. The objectives are to analyze: i) the pattern of agricultural growth, diversity; ii) relative contribution of crop diversification, yield and area towards output growth in the pre-Green Revolution, Green Revolution and Post-Reform period; iii) association of various factors with crop yields in the short run and the adjustment process in the long run. Using secondary data, semi-log linear and spline regression functions we examined the growth and stationarity of growth processes is checked by ADF test. Times series analyses like cointegration and ARDL bound testing approach has been followed to examine the relation of various factors with yield of various crops in the short and long run. The ECM also provides the process of adjustment and CUSUM(Q) test is used for checking fitness of the models. Changes in diversity are analyzed through Herfindahl Index and the additive decomposition technique is employed to examine changing contribution of growth of yield, area and cropping pattern and their interactions. The result reveals varied impacts of main weather variable (rainfall), technological factors and cropping intensity on the yields of crops in different phases since 1950-51. Area effect on output and cropping pattern growth though declined, yield growth contributed increasingly in successive sub-periods in Assam. However, the contribution of modern technology towards the growth has not been uniform in the three major stages of agricultural transformation in Assam.

Influence of Dykes’ Characteristics on Food Crop Production in Lower River Nyando Basin, Kenya

Dykes minimise flood risks among riparian communities. In Nyando basin, Kenya, dykes were constructed to minimise flood impacts on human activities in the riparian plains. The dyke characteristics could change the rate of silting. In spite of these dynamics, some farmers now use fertilisers as a new way of coping with nutrient deficiency. Several researches have been done in Kenya on the effects of floods on human activities; however, there is no clear link between dyke characteristics like period of existence, length and height and their influence on food crop production. The dykes in Nyando have reduced floods in the region; however, it is not clearly understood how the dyke characteristics influence the food crop. Therefore, the purpose of this study was to examine the influence of dyke characteristics on food crop production. Planning Theory was used. Descriptive cross-sectional research design applied. The target population stood at 34,460 households. At least 384 Household heads were recruited via simple random sampling and a questionnaire administered, while purposive sampling was useful in identifying relevant experts in the field of study. Primary data was obtained by interviewing key informants and focused group discussions. Other tools include observation and photography. Secondary data was obtained from publications and print media, and SPSS was utilised in data analysis. Qualitative data was analysed by coding and organisation of data into themes and sub-themes where generalisation was made. The results from the multiple coefficients of determination (R2) indicated that 45.4% (R2 = .454, p = .039) of the variation in the general crop yield was explainable by the combined change in Dyke Characteristics. The dykes’ characteristics significantly influenced crop production

Temporal variation of the relationships between rice yield and climate variables since 1925.

Long-term time-series datasets of crop yield and climate variables are necessary to study the temporal variation of climate effects on crops. The aim of this study was to broadly assess assessment of the effects of climate on rice, and the associated temporal variations of the effects during the long-term period. We conducted field experiments in Taiwan from 1925 to 2019 to collect and analyze rice yield data and evaluate the impacts of changes in average temperature, diurnal temperature range (DTR), rainfall, and sunshine duration on rice yield during cool and warm cropping seasons. We then estimated the relationships between annual grain yield and the climate variables using the time series of their first difference values. We also computed the total relative and annual actual yield changes using regression coefficients for each climate variable for the intervals 1925-1944, 1945-1983, and 1996-2019 to reveal the impacts of climate change on yields and the associated temporal variations during the overall experimental period. The annual daily average temperature calculated from the trend of the regression lines increased by 0.94-1.03 °C during the 95-year period. The maximum temperature remained steady while the minimum temperature increased, leading to decreased DTR. The total annual rainfall decreased by 237-352 mm and the annual total sunshine duration decreased by 93.9-238.9 h during the experimental period. We observed that during the cool cropping season, yield response to temperature change decreased, while that to DTR and rainfall changes increased. During the warm cropping season, all the yield responses to temperature, DTR, and rainfall changes were negative throughout the experimental period. In recent years (1996-2019) the estimated annual actual rice yield changes during the cool cropping season were negatively affected by climate variables (except for sunshine duration), and slightly positively affected (except for temperature) during the warm cropping season. Compared to the effects of temperature and DTR, those of rainfall and sunshine duration on rice yield changes were weak. This study contributes to provide impacts of climate change on rice yield and associated long-term temporal variations over nearly a century.

Spatial relationships between the van Genuchten soil-water retention curve parameters and photosynthetic gas exchange variables in a wheat field

Photosynthetic gas exchange indices can be used to assess spatial variation of crop growth and yield on the field. Spatial variation of soil parameters can be an important tool to assess and manage crop growth status and product quality in the field, given the impact of soil on photosynthetic function. The purpose of this study was to evaluate the spatial relationships between the van Genuchten (vG) soil water retention curve parameters, soil properties and the photosynthetic gas exchange indices in a wheat field with an extension of 200 ha. Different variables of soil and plant were determined at the 100 nodes of a nearly regular grid (150 m × 150 m) over the whole field. The range of variograms showed high variability for photosynthetic parameters and vG parameters, and greater continuity for soil parameters. Photosynthesis was significantly correlated with saturated soil water content (θs) (r = 0.26*), θ1500kPa (permanent wilting point) (0.21*), porosity (r = 0.31**), bulk density (r = −0.32**) and clay content (r = 0.24*). Cross correlogram and linear model of coregionalization of sub-stomatal CO2 concentration (Ci) and stomatal conductance (gs) with photosynthetic rate (A) and transpiration (E) showed opposite relation with soil and hydraulic properties. Regressing of maps showed that a large part of the total variation in A (66%), Ci (79%) and gs (37%) was explained by soil variables. Also, from the visual inspection of the interpolated maps the field can be divided in zones characterized by different soil properties and these maps could be effectively used by farmers to improve wheat yield. On the other hand, results of this study may enhance understanding of the soil properties and soil hydraulic parameters effects on gas exchange parameters of the plant and delineation of the field in homogeneous zones that could be advantageously used by farmers to make informed decisions in site-specific management.

Yield variability across spatial scales in high input farming: Data and farmers’ perceptions for potato crops in the Netherlands

Crop yields are determined by the biophysical environment and by farm management decisions, which in turn depend on socio-economic conditions of the farm(er). The interaction of these factors results in spatial and temporal yield variability. We assessed ware potato yield variability in the Netherlands across four agronomically relevant scales (among provinces, farms and fields and within fields) using five datasets with data on potato yield across space and time. Furthermore, we disseminated an online questionnaire among farmers to identify the perceived yield gap and the key yield gap explaining factors at farm level. Spatial yield variability was largest among fields, with a standard deviation of 8.5–11.1 t ha−1, and within fields, with a standard deviation of 7.7–8.7 t ha−1. Spatial yield variability decreased at higher aggregation levels, i.e., the standard deviation of among-farm yield variability was 4.0–6.1 t ha−1 and that of among-provinces 1.6–3.5 t ha−1. Mean yields of the datasets ranged from 46 to 52 t ha−1. Temporal yield variability explained 10–55 % of the total observed variation in crop yield and its magnitude was equal or larger than the spatial yield variability for almost all datasets. Farmers estimated the ware potato yield gap at 13–18 t ha−1, corresponding to 20–24 % of estimated yield potential, depending on the soil type and variety. Water deficit and water excess were considered the most important yield gap explaining biophysical factors. In addition, soil structure was an important biophysical factor on clay soils and diseases on sandy soils. Irrigation and fertilization were identified as the most important yield gap explaining management factors, whereas legislation and potato prices were identified as the key socio-economic factors influencing potato yields. However, the perceived yield gap explaining factors varied with soil type, variety and year. We conclude that reducing potato yield variability in the Netherlands can be achieved best at the field and within-field level, rather than at farm or regional level. When reducing yield variability is not feasible and/or desirable, inputs should be adapted to actual yield levels to achieve optimal environmental and economic sustainability.

Big data, small explanatory and predictive power: Lessons from random forest modeling of on-farm yield variability and implications for data-driven agronomy

ContextCollection and analysis of large volumes of on-farm production data are widely seen as key to understanding yield variability among farmers and improving resource-use efficiency. ObjectiveThe aim of this study was to assess the performance of statistical and machine learning methods to explain and predict crop yield across thousands of farmers’ fields in contrasting farming systems worldwide. MethodsA large database of 10,940 field-year combinations from three countries in different stages of agricultural intensification was analyzed. Random effects models were used to partition crop yield variability and random forest models were used to explain and predict crop yield within a cross-validation scheme with data re-sampling over space and time. ResultsYield variability in relative terms was smallest for wheat and barley in the Netherlands and for wheat in Ethiopia, intermediate for rice in the Philippines, and greatest for maize in Ethiopia. Random forest models comprising a total of 87 variables explained a maximum of 65 % of cereal yield variability in the Netherlands and less than 45 % of cereal yield variability in Ethiopia and in the Philippines. Crop management related variables were important to explain and predict cereal yields in Ethiopia, while predictive (i.e., known before the growing season) climatic variables and explanatory (i.e., known during or after the growing season) climatic variables were most important to explain and predict cereal yield variability in the Philippines and in the Netherlands, respectively. Finally, model cross-validation for regions or years not seen during model training reduced the R2 considerably for most crop x country combinations, while for wheat in the Netherlands this was model dependent. ConclusionBig data from farmers’ fields is useful to explain on-farm yield variability to some extent, but not to predict it across time and space. SignificanceThe results call for moderate expectations towards big data and machine learning in agronomic studies, particularly for smallholder farms in the tropics where model performance was poorest independently of the variables considered and the cross-validation scheme used.

Role of sea surface temperature variability on the risk of Canadian wheat, barley, and oat yields

Surface air temperature (SAT) and precipitation in Prairie (Western) and Maritime (Eastern) Canada are influenced by the El Niño Southern Oscillation (ENSO) and Atlantic Multidecadal Oscillation (AMO), respectively. However effects of ENSO and AMO on major crop yield in Canada is yet to be understood. Here we investigate the longest record (1908–2017) of wheat, barley, and oat yield as well as its associated risk with summer (May-September) ENSO and AMO interannual and multidecadal variability in Prairie and Maritime, respectively. We used generalized linear models with autocorrelative residuals to assess region- and crop-specific associations between ENSO, AMO, surface air temperatures, and precipitation on crop yield. After adjusting for covariates our models show that a positive phase of the AMO (in comparison to negative phase) significantly reduces the risk of Maritime crop yields by ~3–12%, with both extreme heat and wet precipitation found to be significant risk factors for reducing yields. Summer El Niño or La Niña was found to have a small, insignificant effect on yield in the Prairie region, with no effects found on crops in Maritimes. Therefore, analysis of Atlantic oceanic variability can offer insight into major crop yield variability in Maritime Canada.

Responses of total, reactive and dissolved phosphorus pools and crop yields to long-term fertilization

Maintaining an appropriate soil phosphorus level is key to ensure sustainable phosphorus management for crop production and to minimise phosphorus losses to water bodies. However, the effects of long-term fertilization on different soil phosphorus pools, crop yields and phosphorus loss risk remain unclear. This requires insights into the responses of soil phosphorus pools, crop phosphorus uptake with related crop yields and phosphorus loss to long-term phosphorus inputs. Changes in four soil phosphorus pools (PCACL2, POLSEN, POX and PTOTAL, respectively) and crop yield responses to various fertilization rates were examined in a 29-year long-term phosphorus fertilization experiment in China. Results showed that the increase in the four soil phosphorus pools was proportional to the accumulated phosphorus surplus, i.e., the input minus uptake. POLSEN and POX increased linearly with continuous phosphorus application and peaked at a phosphorus accumulation near 3200 kg P ha−1. Beyond this threshold, continuous phosphorus application caused a gradual increase in PTOTAL and a linear increase in PCACL2, which implies an increasing risk for leaching. The POX pool accounted for 87% of the accumulated phosphorus surplus until soil phosphorus saturation occurred. The crop yields of wheat and maize responded clearly to changes in PTOTAL, POX, POLSEN and PCACL2, with POX explaining most of the yield variation. Furthermore, POX was highly correlated with PCACL2, being a risk indicator for phosphorus leaching. Given that POX explains best how much of phosphorus surplus accumulates in soil, the variation in crop yield, and the risk for P leaching, it can be used as a valuable and reliable indicator to manage phosphorus sustainably.

CROP YIELD PREDICTION BASED ON MACHINE LEARNING

In order to find relevant information and draw recommendations, the data analysis process involves analyzing, cleaning, and modeling the data. India has a large population, hence it is important to protect the world's food supply despite climate fluctuations.Framers face serious problems in drought conditions.The agricultural output is significantly influenced by the kind of soil. Advising farmers to utilize fertilizers might assist them in making the best choice possible for their farming circumstances. There are several studies Information and Communication Technology (ICT) may be used for agricultural yield prediction. We can also anticipate the agricultural production by using data mining. We can advise the farmer to plant a better crop for a higher yield by thoroughly analyzing the prior data. Information from traditional farmers is transferred to educated farmers through smart agriculture. to calculate estimates of overall physical production functions for the yields of various crops in a given condition, taking into account a newly designed weather index as an input.To adequately compare our actual result, also known as the target, with the prediction model, which provides farmers with the analysis of rice production based on available data, regression and coefficient of determination analysis as well as average error rate were conducted. To increase crop production, several data mining approaches were employed to estimate the crop output. For operational projects, it is crucial to accurately and promptly evaluate the state of agricultural crops and predict possible crop yields. The goal of this study is to employ a variety of forecasting techniques to assess agricultural yield estimations in Ghana due to the significance of crop yield prediction. Crop yield prediction, which offers information to decision-makers.

Long time-series variation of crop yield under drought stress and drought vulnerability curves in Songnen Plain, Northeast China

It is of practical significance to reveal the long-term characteristics of drought and its impacts on crop yield in Songnen Plain, an important commodity grain base in Northeast China. This study firstly explored the long time-series variation of Modified Soil Water Deficit Index (MSWDI) and crop yield at multiple sites in Songnen Plain during 1960–2014 based on numerical simulation with the World Food Studies (WOFOST) model. This study then revealed the mutation of the drought and crop yield with three mutation point test methods, and thereafter explored their relationship between the drought and crop yield with the cross wavelet transform (XWT) and drought vulnerability curve. Results suggested the precipitation was at the lowest level in the 1970 s, which significantly increased in the 1980 s and thereafter exhibited a slow declining trend. Mutation points of drought conditions occurred at multiple stations in 1983, and the crop yields also showed obvious mutation in 1983 or 1984 at two stations. Besides, the drought and crop yield had significant 2–4 year resonance cycles during 1978–1980 at four stations. In particular, periods with high correlation between these two variables were generally years prone to abrupt changes. In addition, determination coefficients of the drought vulnerability curves based on the linear function, cubic curve function and hyperbolic tangent function reached 0.55, 0.65, and 0.64, respectively, suggesting the cubic curve function performed best. The drought vulnerability curve based on the cubic curve function suggested the crop yield loss showed a firstly decreasing and then increasing trend, which may be related to the compensation mechanism of crops. Overall, combination of the mechanistic drought index and crop models provides an effective way to reveal impacts of drought stress on crop yield and offer support information for coping with drought.

DEPENDENCE OF PRODUCTIVITY OF AGRICULTURAL PRODUCTION IN UKRAINE ON CHANGES IN THERMAL REGIME

The dynamics of changes in the average annual air temperature in 24 regions of Ukraine in the period 2011 - 2020 is analyzed. The correlation between the yield of major crops and the average annual air temperature is studied. The regional features of this dependence are analyzed. The regions of the country are ranked according to the degree of correlation between the average annual temperature and crop yields.
 Agriculture is largely dependent on natural factors, the most important of which is the change in agro-climatic conditions due to modern climate change. The main manifestation of modern climate change is an increase in air temperature, and in Ukraine the temperature increase is much more intense than in most regions of the world. Given the significant contribution of the agricultural sector to the economy of Ukraine, the problem of the dependence of agricultural production on changes in the thermal regime is of particular relevance.
 The article discusses the impact of changes in the thermal regime on the territory of Ukraine on the productivity of major agricultural crops. The average annual air temperature is used as an indicator characterizing the thermal regime of the territory. The dynamics of the average annual temperature in twenty-four regions of Ukraine in the period from 2011 to 2020 is analyzed. In particular, the regions of the most intensive increase in temperature have been identified. The relationship between the average annual air temperature and the productivity of the main agricultural crops, which include potatoes, sunflowers, as well as cereals and legumes, vegetables, fruit and berries, has been studied. To identify the relationship between temperature and yield, the method of pair correlation was used. The calculations were carried out using a Microsoft Excel spreadsheet.
 The study revealed significant differences in the degree of dependence of the yield of different crops on temperature conditions. It has been proven that the nature of the influence of thermal conditions on yield can vary significantly depending on the type of crop. In particular, the current increase in temperature favorably affects the efficiency of growing cereals and legumes and, at the same time, leads to a significant decrease in potato yield. It is shown that the dependence of the yield of different crops on air temperature is characterized by significant territorial disproportions. Wherein, the regions with the highest indicators of correlation dependence are located mainly in the west and northwest of Ukraine.
 The regions of Ukraine were ranked in accordance with the total degree of correlation between the average annual air temperature and the yield of selected agricultural crops. When ranking regions according to the degree of influence of the thermal factor, the arithmetic mean of the absolute values ​​(modules) of the correlation coefficients was used. According to the ranking results, the regions were grouped. It has been proved that when analyzing territorial disproportions, it is necessary to take into account the differences in the agricultural specialization of the regions, since the specialization of crop production causes significant differences in the sown areas of crops with different dependence on thermal factors.
 Based on the study, we can conclude that the current change in the thermal regime already has a significant impact on the process of transformation of agriculture, which, in particular, is manifested in a change in the agricultural specialization of the regions. For example, in regions specializing in the cultivation of vegetable crops, an increase in air temperature leads to a decrease in the efficiency of agricultural production. In turn, the decrease in the efficiency of agricultural production leads to a decrease in the volume of production. At the same time, the increase in the thermal resources of Polesye makes it possible to grow sunflower and other heat-loving crops in this zone.
 The novelty of the study is to obtain a comprehensive assessment of the influence of the thermal factor on the yield of various crops. At the same time, it should be noted that the main result of the study is obtaining a numerical characteristic of the degree of correlation dependence, which allows analyzing the degree of dependence of different crops on temperature conditions, as well as identifying and analyzing territorial disproportions in the distribution of this dependence.
 Key words: yield, average annual air temperature, specialization of agriculture.

A Spatially Explicit Evaluation of the Economic Performance of a Perennial Energy Crop on the Marginal Land of the Loess Plateau and China

The Loess Plateau, with a large area of marginal land, holds the potential to produce 62–106 Tg per year of switchgrass biomass; however, the economic feasibility of producing bioenergy in the region is unclear. The farm-gate feedstock production (FGFP) cost of switchgrass was calculated in a spatially explicit way by taking the geographic variation in crop yield, soil properties, land quality, and input costs into consideration in order to evaluate the economic performance of bioenergy production. Cost–supply curves were constructed to explore the energy supply potential of switchgrass feedstock. The calculations were conducted using ArcGIS in a 1 km grid and all the evaluations were conducted under different agricultural management practice (AMP) scenarios in parallel. The FGFP costs showed significant spatial variation ranging from 95 to 7373 CNY (Chinese Yuan) per tonne−1 and that the most economically desirable areas are scattered in the south and southeast region. The weighted average FGFP costs are 710, 1125, and 1596 CNY per tonne−1 for small bale (SB), large bale (LB), and chipping (CP) harvest methods, respectively. The projected energy supply potential is 1927 PJ (Petajoules) per year−1, of which 30–93% can be supplied below the market prices of different fossil fuels according to feedstock formats. Compared to current biomass residual pricing, 50–66 Tg (Teragrams) switchgrass feedstock is competitive. The results demonstrated that the Loess Plateau holds the potential to produce bioenergy that is economically feasible. This study provides a methodological framework for spatially explicit evaluation of the economic performance of perennial energy crops. Detailed information obtained from this study can be used to select the optimal locations and AMPs to produce feedstock production at minimum cost.

Enhancing resilience to climate change through prospective strategies for climate-resilient agriculture to improve crop yield and food security

It is important to highlight that agriculture is one of the sectors that will be directly affected by climate change scenarios in recent years. There are a number of processes such as drought, floods, temperature, salinity etc along with other forms of biotic factors posing significant impacts on crop yields of various crops due to their fluctuating scenario in the environment. Espousal of smart technologies and practices like smart crop and variety selection, efficient climate-based cropping system, agricultural water management (AWM), balanced fertilization, contingency planning, recarbonization of soils, no-till system, integrated farming system, site specific nutrient management etc are being advised to exercise in many regions for climate-resistant agriculture. These approaches minimize soil disruption and energy usages, enhance soil health and alleviate greenhouse gas discharges, minimize unproductive losses and improve efficiency of land and water use result in greater crop production with reduced fertilizer usage. As a part of this strategy, weather stations and mini-weather lookouts are set up at the village stage to register relevant weather observations like temperature, rainfall, wind speed and relative humidity etc to furnish customized agro-advisories to farmers, which reduce detrimental consequences attributed to the climate. A climate smart approach integrates farmer’s practices with related technologies, plans, institutes, policies and financial packages. So, initiating the choice of site-specific crops, development of customized technologies and tools, diversification of crops, improvement of climate-resistant crop varieties, syndication of forecasting tools and proper management of resources at the community level can effectively enhance climate resilience in agriculture.

Long-Term Nutrient Cycle in Improved Grain Yield of Dryland Winter Wheat (Triticum aestivum L.) under Hydrological Process of Plant Ecosystem Distribution in the Loess Plateau of China.

Precipitation is the major cause of crop yield variation in rainfed agriculture production in the Loess Plateau. As over fertilization is economically and environmentally undesirable, and crop yield and the resulting returns for N input are uncertain when rainfall variability is high, optimizing N management according to precipitation during fallow season is vital for efficient crop water use and high yield in dryland rainfed farming systems. Results show that the nitrogen treatment rate of 180 treatment significantly increased the tiller percentage rate, and the leaf area index at anthesis, the jointing anthesis, anthesis maturity dry matter, and nitrogen accumulation was closely related to yield. N150 treatment compared to N180 treatment significantly increased the percentage of ear-bearing tiller by 7%, dry substance accretion from jointing to anthesis by 9%, and yield by 17% and 15%, respectively. Our study has important implications for the assessment of the effects of fallow precipitation, as well as for the sustainable development of dryland agriculture in the Loess Plateau. Our results indicate that adjusting N fertilizer inputs based on summer rainfall variation could enhance wheat yield in rainfed farming systems.

Isolation and Screening of Agriculturally Important Bacteria (PGPR) from Organic Sources of Nutrient (Panchgavya, Jeevamrit and Farm Yard Manure) for Future Use

Agriculture is an essential component to maintain the human health but due to sudden increase in population the demand has increased and to meet the requirement the use of chemical fertilizer has also increase. The continuous use of chemical fertilizer and pesticides degrade the quality and fertility of soil and also reduce the yield of various crops. The organic sources such as panchgavya, jeevamrit and Farm Yard Manure consists load of beneficial microorganisms that promote the plant growth, yield and promote natural resources. The present study was carried out by isolating the bacteria from organic sources (panchgavya, jeevamrit and FYM) because minute amount of bacterial culture is suffient to prepare large one according to need and can be stored for longer time as compare to organic input. The samples of panchgavya, jeevamrit and FYM were collected from different location of Himachal Pradesh. A total of 32 bacterial isolates from panchgavya, 43 from jeevamrit and 59 from FYM were isolated and screened for multiple plant growth promoting traits. Only 4 bacterial isolates from panchgavya, 2 from jeevamrit and 2 from FYM were preferred on the basis of maximum plant growth promoting traits like P-solubilization, Nitrogen fixer, Siderophore production, HCN production, IAA production and Antifungal activity. From the selected bacterial isolates 67.78% were P- solubilizers, 60.37% were Nitrogen fixer, 62.37% were Siderophore producer, 34.29% HCN producer, 45.88% IAA producer and 78.22% show antagonism against Pythium graminicolum and 74.81% show antagonism against Collectotrichum capsici. Hence these bacterial isolates have potential to act as biofertilizer for environment friendly sustainable agriculture systems and alternative to harmful chemicals.

Optimization of Crop Recommendations Using Novel Machine Learning Techniques

A farmer can use machine learning to make decisions about what crops to sow, how to care for those crops throughout the growing season, and how to predict crop yields. According to the World Health Organization, agriculture is essential to the nation’s quick economic development. Food security, access, and adoption are the three cornerstones of the organization. Without a doubt, the main priority is to ensure that there is enough food for everyone. Increasing agricultural yield can help ensure a sufficient supply. The country-wide variation in crop yields is substantial. As a result, this will be the foundation for research into whether cluster analysis can be used to identify crop yield patterns in a field. Previous study investigations were only marginally successful in accomplishing their primary intended objectives because of unstable conditions and imprecise methodology. The vast majority of farmers base their predictions of crop yield on prior observations of crop growth in their farms, which can be deceptive. Standard preprocessing methods and random cluster value selection are not always reliable, according to the literature. The proposed study overcomes the shortcomings of conventional methodology by highlighting the significance of machine learning-based classification/partitioning and hierarchical approaches in offering a trained analysis of yield prediction in the state of Karnataka. The dataset used for the study was collected from the ICAR-Taralabalu Krishi Vigyan Kendra, Davangere, Karnataka. In the two dataset analysis techniques employed in the study to find anomalies, crop area, and crop production are significant variables. Crop area and crop yield are important variables in the two dataset analysis methods used in the study to detect anomalies. The study emphasizes the importance of a mathematical model and algorithm for identifying yield trends, which can assist farmers in selecting crops that have a large seasonal impact on yield productivity.

Effects of 18 years repeated N fertilizer applications on gross N transformation rates in a subtropical rain-fed purple soil

In this study, a 15N tracing experiment was conducted to determine gross N transformation rates in soils with 18 years of repeated N fertilizer applications and to quantify the underlying mechanisms to explain the variability of crop yield in a subtropical rain-fed purple soil. Six N fertilizer treatments were evaluated: unfertilized control (CK), mineral N fertilizer (NPK), pig manure (OM), mineral N fertilizer plus pig manure (OM-NPK), crop residue (RSD) and mineral N fertilizer plus crop residue (RSD-NPK). The results showed that the soil organic carbon (SOC) concentration in OM (average 13.79 g kg−1) and RSD-NPK (average 13.15 g kg−1) were significantly higher than the other treatments (varied from 5.91 to 11.23 g kg−1) after 18 years. Higher maize yields were observed in NPK, OM, OM-NPK, and RSD-NPK, and especially in RSD-NPK and OM-NPK after 18 years, compared with the data measured in the 11th years. Soil gross N mineralization rates (M) were significantly higher in all N fertilizer treatments (varied from 13.00 to 31.17 mg N kg−1 soil d−1) compared to CK (average 5.53 mg N kg−1 soil d−1). After 18 years of repeated N fertilizer applications, M were significantly higher than those in the 11th years for the same N fertilizer treatment, indicating that long-term repeated N fertilizer application, whether mineral N or organic fertilizer, continuously enhances M. M was positively correlated with SOC (p < 0.05) and total N (TN) (p < 0.05), suggesting that soil organic substrates are key factors regulating M. Maize yield was positively correlated with M (p < 0.05), suggesting that available N produced through soil N mineralization played the important role in yield formation. All N fertilizer treatments continuously stimulated gross autotrophic nitrification rates (ONH4). ONH4 increased with increasing M (p < 0.01) and ammonia-oxidizing bacteria (AOB) abundance (p < 0.05). However, compared to the 11th year, rates of dissimilatory nitrate reduction to ammonium (DNRA) and immobilization of NH4+ (except RSD) and NO3− (except OM-NPK) decreased significantly in the N fertilizer treatments in the 18th year, indicating that N retention capacity is reduced over time and the risk of N losses increased. Considering the best balance among food security, soil C sequestration, and reduction of N leaching, mineral N in combination with straw return (RSD-NPK) can be recommended for regions with similar soils and climates.

Agricultural Grid Connected Photovoltaic System Design and Simulation in Egypt by using PVSYST Software

Agricultural Photovoltaic Systems are a key technology to achieve sustainable development goals by reducing competition between land for food and electricity. In addition, Agricultural Photovoltaic Systems are at the heart of the link between power generation, crop production and irrigation water conservation. The main ecophysiological constraint on crop production under photovoltaics is the reduction of light. It is difficult to recommend shade tolerance for some plant varieties due to insufficient information on shading conditions for most plants. The use of shading panels (photovoltaic panels) requires more crop-specific research to determine the optimal percentage of panels and their placement that will not reduce agricultural yields. Crop yield variation versus field shading and availability to maximize the system require extensive research. This study aims to develop a standard procedure for designing an agricultural grid-connected photovoltaic power generation system for solar power generation in an agricultural area in Bahteem, Egypt. The technical and annual performance of the grid-connected PV system was simulated using PV Syst software. The paper started with a pre-feasibility study of a grid-connected photovoltaic system using PV Syst. Software with an extensive database of meteorological data, including global daily horizontal solar irradiance, and a database of various renewable energy system components from different manufacturers. In this work, a comprehensive literature review of agricultural solar photovoltaic systems is conducted, with a particular focus on grid-connected systems, followed by a design procedure for grid-connected solar photovoltaic systems. The planned photovoltaic system will generate a total of 400 KWp of electricity. This generated electricity can drive down electricity prices by exporting excess electricity to the national grid. In addition, solar power systems are fuel-efficient and have a low environmental impact.