Agrometeorological Data Research Articles

Rice Yield Estimation Using Machine Learning and Feature Selection in Hilly and Mountainous Chongqing, China

To investigate effective techniques for estimating rice production in hilly and mountainous areas, in this study, we collected yield data at the field level, agro-meteorological data, and Sentinel-2/MSI remote sensing data in Chongqing, China, between 2020 and 2023. The integral values of vegetation indicators from the rice greening up to heading–filling stages were determined using the Newton–trapezoidal integration method. Using correlation analysis and importance analysis of permutation features, the effects of agro-meteorological variables and vegetation index integrals on rice yield were assessed. The chosen characteristics were then combined with three machine learning techniques—random forest (RF), support vector machine (SVM), and partial least squares regression (PLSR)—to create six rice yield estimate models. The results showed that combined vegetation indices were more effective than indices used in separate development phases. Specifically, the correlation coefficients between the integral values of eight vegetation indices from rice greening up to heading–filling stages and rice yield were all above 0.65. By introducing agro-meteorological factors as new independent variables and combining them with vegetation indices as input parameters, the predictive capability of the model was evaluated. The results showed that the performance of PLSR remained stable, while the prediction accuracies of SVM and RF improved by 13% to 21.5%. After feature selection, the inversion performance of all three machine learning models improved, with the RF model coupled with variables selected during permutation feature importance analysis achieving the optimal inversion effect, which was characterized by a coefficient of determination of 0.85, a root mean square error of 529.1 kg/hm2, and a mean relative error of 5.63%. This study provides technical support for improving the accuracy of remote sensing-based crop yield estimation in hilly and mountainous regions, facilitating precise agricultural management and informing agrarian decision making.

Climate and disease: tackling coffee brown-eye spot with advanced forecasting models.

Climate influences the interaction between pathogens and their hosts significantly. This is particularly evident in the coffee industry, where fungal diseases like Cercospora coffeicola, causing brown-eye spot, can reduce yields drastically. This study focuses on forecasting coffee brown-eye spot using various models that incorporate agrometeorological data, allowing for predictions at least 1 week prior to the occurrence of disease. Data were gathered from eight locations across São Paulo and Minas Gerais, encompassing the South and Cerrado regions of Minas Gerais state. In the initial phase, various machine learning (ML) models and topologies were calibrated to forecast brown-eye spot, identifying one with potential for advanced decision-making. The top-performing models were then employed in the next stage to forecast and spatially project the severity of brown-eye spot across 2681 key Brazilian coffee-producing municipalities. Meteorological data were sourced from NASA's Prediction of Worldwide Energy Resources platform, and the Penman-Monteith method was used to estimate reference evapotranspiration, leading to a Thornthwaite and Mather water-balance calculation. Six ML models - K-nearest neighbors (KNN), artificial neural network multilayer perceptron (MLP), support vector machine (SVM), random forests (RF), extreme gradient boosting (XGBoost), and gradient boosting regression (GradBOOSTING) - were employed, considering disease latency to time define input variables. These models utilized climatic elements such as average air temperature, relative humidity, leaf wetness duration, rainfall, evapotranspiration, water deficit, and surplus. The XGBoost model proved most effective in high-yielding conditions, demonstrating high precision and accuracy. Conversely, the SVM model excelled in low-yielding scenarios. The incidence of brown-eye spot varied noticeably between high- and low-yield conditions, with significant regional differences observed. The accuracy of predicting brown-eye spot severity in coffee plantations depended on the biennial production cycle. High-yielding trees showed superior results with the XGBoost model (R2 = 0.77, root mean squared error, RMSE = 10.53), whereas the SVM model performed better under low-yielding conditions (precision 0.76, RMSE = 12.82). The study's application of agrometeorological variables and ML models successfully predicted the incidence of brown-eye spot in coffee plantations with a 7 day lead time, illustrating that they were valuable tools for managing this significant agricultural challenge. © 2024 Society of Chemical Industry.

Comparing Remote and Proximal Sensing of Agrometeorological Parameters across Different Agricultural Regions in Croatia: A Case Study Using ERA5-Land, Agri4Cast, and In Situ Stations during the Period 2019–2021

The paper evaluates the usability of remote satellite-based and proximal ground-based agrometeorological data sources for precision agriculture and crop production in Croatia. The compared agrometeorological datasets stem from the open-access data sources Copernicus CDS and the Agri4Cast portal, and commercial in situ agrometeorological stations (PinovaMeteo) which monitor environmental parameters relevant to the physiological state of crops. The study compares relevant parameters for 10 different locations in Croatia for three consecutive years (2019, 2020, and 2021) to investigate whether model-based data from ERA5-Land and Agri4Cast are well-correlated with ground measurements from independent in situ stations (PinovaMeteo) for specific agrometeorological parameters (air and soil temperature, and precipitation). Our results indicate the following: both the ERA5-Land and Agri4Cast datasets show mostly strong positive correlations with ground observations for air temperature, modest correlations for soil temperature, but modest or even low correlations for precipitation. Analysis of the residuals indicates higher overall residual values, especially in areas with complex topography and near large bodies of water or the sea, and deviations of residuals that may limit the usability of satellite- and model-based data for decision-making in agriculture.

Forecast sugarcane maturity from agrometeorological data and soil water storage

The environment (climate and soil) can stimulate the accumulation of sugars in the cane, inducing the plant´s maturation process. In this way, we can estimate sugarcane maturity based on the crop's growth response to environmental conditions, which allows us to quantify the raw material (ethanol or sugar) and plan the harvest. The aim of this study was to evaluate the effects of agrometeorological variables and soil water storage on the sugarcane maturation process and to generate forecasting models for soluble solids content (°Brix) and total recoverable sugars (TRS, kg t-1). The experiment was carried out in the Santo Antonio de Goiás, Brazil. We evaluated °Brix and TRS of the sugarcane cycles (cane-plant, 1st ratoon, 2nd ratoon). The agrometeorological data was obtained from a weather station, which made it possible to calculate the crop’s water balance and degree-day. All the variables were subjected to multivariate statistical analysis, which selected the most significant variables. The models used degree-days, reference evapotranspiration and soil water storage as independent variables, which obtained multiple coefficients of determination (R_p^2) greater than 0.60. The estimates showed a good fit for both °Brix and TRS models, which determined a mean absolute error (MAE) of 1.15 °Brix and 9.88 kg t-1, respectively; and very good confidence index (c > 0.75). Independent estimates obtained MAE < 2.60 ºBrix, while TRS resulted in MAE < 21.30 kg t 1, with “c” ranging from good to optimum (c > 0.70). Models based on multivariate analysis can be used to estimate the sugarcane harvest point based on the sugar content in the stalks, agrometeorological variables and soil water storage.

Использование агрометеорологических данных для обоснования оросительных мелиораций саженцев плодовых и ягодных культур в Центральном Нечерноземье

Irrigation is important when growing planting material in fruit and berry nurseries, which are located in areas of insufficient or unstable moisture, as well as in the central part of the non-chernozem zone of Russia due to the uneven distribution of precipitation during the season. The purpose of the study is to substantiate the need for irrigation reclamation of seedlings of fruit and berry crops in the central Non-black earth region using agrometeorological data. Research on the development of drip irrigation technology for seedlings of fruit and berry crops was carried out in the Michurinsky garden of the Russian State Agrarian University – Moscow Timiryazev Agricultural Academy. The study uses observational data (air temperature, precipitation, relative air humidity) obtained at the Mikhelson Meteorological Observatory, for 2018‑2023. To assess the provision of heat and moisture to individual periods of the growing season, the Selyaninov hydrothermal coefficient was calculated. a and Shashko moisture coefficient. As a result of the analysis of agrometeorological data, the need for irrigation in the conditions of the central non-chernozem zone of Russia was proven. The number of days with productive precipitation of more than 5 mm is 39% of the total number of days on which precipitation fell, and its distribution during the growing season is uneven, which may coincide with hot periods when plants are characterized by increased water consumption.

Changes in agro-climatic characteristics and their impact on crop yields in the Saratov region

The sustainable development of agricultural production in the conditions of global climate warming is largely determined by the timely provision of up-to-date agrometeorological information. To process and interpret long-term agrometeorological data with their geographical reference, it is advisable to use the tools of geographical information systems. The article presents a method of interpretation of agrometeorological information by means of geoinformation technologies. A comparative characteristic of the probability of droughts of strong and very strong intensity in separate periods of the growing season for 1971-2000 and 2001-2021 for the natural zones of the Saratov region was given. The initial material was the climatic data on the weather stations of the Saratov region. The yield data were taken from statistical collections. Geospatial analysis of long-term climatic indicators allowed us to present their spatial distribution at the regional level.

Performance of the Copernicus European Regional Reanalysis (CERRA) dataset as proxy of ground-based agrometeorological data

The continuous advances in numerical modeling of the atmosphere, computing power and data assimilation techniques entail frequent updates of numerical weather prediction (NWP) models that show improved forecast skill. This circumstance leads to the recurrent delivery of revised reanalysis databases that provide weather estimates for several decades back in time by combining the latest NWP models with observations. Since climate studies and agriculture water management applications require the availability of accurate and reliable weather data, assessing the performance of reanalysis products contributes to informed choices of potential weather proxy of ground-based agrometeorological data. CERRA (Copernicus European Regional ReAnalysis) dataset is the latest regional reanalysis product released by the European Centre for Medium-Range Weather Forecasts (ECMWF), in August 2022. CERRA is forced by the global ERA5 reanalysis, and it provides weather data with resolution of 5.5 km for the pan-European territory from 1984. For the first time in literature, this study explores the performance of CERRA data at 38 ground-based weather stations located in Sicily, an Italian region with Mediterranean climate, during the irrigation seasons 2003–2022. The objective of the study lies in evaluating CERRA performance with respect to air temperature, actual vapor pressure, wind speed and solar radiation that are input variables for assessing reference evapotranspiration, ETO, which is a key variable for quantifying irrigation volumes needed for water resources studies. The accuracy of ETO estimates depends on those input variables through the equation provided by the Food and Agriculture Organization of the United Nations (FAO), i.e., the FAO Penman-Monteith equation. Here, it is also evaluated the performance of ETO estimates by using CERRA weather inputs in the FAO Penman-Monteith equation. The results show that the performances of CERRA weather data are excellent, especially for air temperature, and this determines that CERRA ETO estimates present high accuracy and reliability with a mean PBIAS and NRMSE equal to 5.6% and 13%, respectively, over the region. Those outcomes lead to the conclusion that CERRA dataset represents a valid alternative to ground-based agrometeorological measurements and their spatial interpolation for water resource regional studies.

Characteristic Identification of Heat Exposure Based on Disaster Events for Single-Season Rice along the Middle and Lower Reaches of the Yangtze River, China

As global warming continues, heat stress events are expected to increase and negatively affect rice production. Spatiotemporal changes in single-season rice exposure to heat stress were explored along the middle and lower reaches of the Yangtze River (MLRYR) in China during 1971–2020 based on created heat thresholds in different phenological stages, derived from comparison of historical heat records for single-season rice and agro-meteorological data. The feature importance (IF) provided by the Random Forest model was used to modulate the relationship between threshold accumulated temperature and yield reduction rate caused by heat stress. In addition, critical temperature thresholds at different phenological stages were determined by combining Overall Accuracy and the Receiver Operating Characteristic (ROC) curve. According to historical disaster records, the heat stress occurred before the reproductive phase (i.e., the tillering–jointing stage) and ended in the filling stage. Critical temperature thresholds of Tmax at tillering–jointing, booting, flowering and filling were quantified as 36, 35, 35 and 38 °C, with higher IF values of 13.14, 10.93, 17.15 and 13.15, respectively. The respective values of Overall Accuracy and the areas under the ROC curve were greater than 0.85 and 0.930, implying that each threshold performed excellently in identifying heat occurrence. Based on the determined critical thresholds, accumulated harmful temperature (Tcum), number of heat days (HD), first heat date (FHD) and last heat date (LHD) were presented to characterize heat exposure. It was clear that Tcum and HD exhibited a north-to-south increasing trend from 1971 to 2020, with the obvious increasing occurrence in most parts of the study region through the period of 2010 to 2020. FHD occurred earlier in most stations except the northeast parts, while LHD ended later in southern MLRYR. Exploring heat critical thresholds at different phenological stages highlighted in this study can help decision-makers monitor and evaluate heat exposure to single-season rice in MLRYR and further develop mitigation strategies to ensure rice production security.

Climate Change Perception and Innovative Mitigation Practices Adopted by Hungarian Farms

Climate change is becoming a growing concern for the agricultural sector. Variable weather events, such as droughts and floods, are expected to have a significant negative impact on agricultural losses, earnings and consumption. The agriculture industry in Europe is not immune to these difficulties. This study focuses on Hungary, a country with a strong agricultural focus that, as a result, is particularly susceptible to climate change. An exploratory factor analysis (EFA) was performed to synthesis data about the perspectives of Hungarian farmers on the dangers of climate change. Then, latent variables were employed as explanatory variables in the Logit model to investigate the link between the perceptions of climate change risks by Hungarian farmers and their inclination to adopt innovative ways to mitigate its repercussions. Changes in temperature and precipitation, economic damage, water damage, and insect damage are seen as the most serious repercussions of climate change by Hungarian farmers. These beliefs raise the possibility of adopting new strategies to offset harmful consequences, including (i) the adoption of new varieties, (ii) ice and frost protection, and (iii) the use of agro-meteorological data. The results show that the chance of adopting new varieties is substantially influenced by farmers’ assessments of harm caused by pests, pathogens, and illnesses (2.91***). In contrast, water damage concerns seem to have a significant impact on the adoption of novel approaches to reduce cold and frost damage (2.18***). This study’s findings support the efforts of stakeholders and policymakers to encourage the dissemination of technology to protect crops from climate change in Hungary and imply that governments should provide financial incentives to farmers to boost innovation uptake.

Growth of aridity and development of integrated land reclamation in the Republic of Tatarstan

Subject. The article addresses problems of organization of efficient and stable agricultural production in conditions of climate aridity in the Volga region. Objectives. The aim is to review the current state of the land reclamation industry in the Republic of Tatarstan, to elaborate recommendations for its further development. Methods. The study employs methods of comparison, systematization, and generalization of data. Results. We investigated the dynamics of agrometeorological data for 2006–2020 in the Republic of Tatarstan and revealed a trend towards an increase in climate aridity in the Volga region. The assessment of economic efficiency of irrigated agriculture enabled to state that potato yield increases by four times due to irrigation. Watering perennial crops helps provide the livestock industry with a reliable feed base. Conclusions. Despite the high economic efficiency of agricultural land reclamation, the number of agricultural producers introducing it into production activities remains low due to the high cost of restoration, construction and operation of land reclamation facilities, scarce technical and financial resources at agricultural enterprises.

M2F-Net: A Deep Learning-Based Multimodal Classification with High-Throughput Phenotyping for Identification of Overabundance of Fertilizers

Amaranth, a pseudocereal crop which is rich in nutrients and climate resistant, can provide an opportunity to increase food security and nutritional content for the growing population. Farmers rely mainly on synthetic fertilizers to improve the quality and yield of the crop; however, this overuse harms the ecosystem. Understanding the mechanism causing this environmental deterioration is crucial for crop production and ecological sustainability. In recent years, high-throughput phenotyping using Artificial Intelligence (AI) has been thriving and can provide an effective solution for the identification of fertilizer overuse. Influenced by the strength of deep learning paradigms and IoT sensors, a novel multimodal fusion network (M2F-Net) is proposed for high-throughput phenotyping to diagnose overabundance of fertilizers. In this paper, we developed and analyzed three strategies that fuse agrometeorological and image data by assessing fusion at various stages. Initially two unimodal baseline networks were trained: Multi-Layer Perceptron (MLP) on agrometeorological data and a pre-trained Convolutional Neural Network (CNN) model DenseNet-121 on image data. With these baselines, the multimodal fusion network is developed, capable of adeptly learning from image and non-image data and the model’s performance is evaluated in terms of accuracy and Area Under Curve (AUC). Moreover, the fusion approaches that are considered outperformed the unimodal networks remarkably with 91% accuracy. From the experimental result, it is proven that incorporating agrometeorological information and images can substantially boost the classification performance for the overabundance of fertilizer.

Monitoring of crop water consumption changing based on remotely sensed data and techniques in North Sinai, Egypt

This paper aims to approximate and verify crop water use based on satellite results. Land Surface Temperature (LST) and Normalized Difference Vegetation Index (NDVI) were used as the critical parameters derived from NOAA/AVHRR and landsat8 satellite data. Reference evapotranspiration (ETo) was determined using FAO-Penman-Monteith (FPM) agrometeorological data as a standard process. Based on data from remote sensing, the ETo was calculated based on the Hargreaves (Har) process. ETo-FPM has been used to calibrate ETo-Har under the same conditions for five years (2002-2006). Landsat8 data was obtained on 25 June 2013 and 28 June 2014 and used to estimate the crop coefficient (Kc) based on satellite data (Kc-Sat). The LST was used to predict the maximum, minimum, and mean Tair (oC) levels in June 2013 and 2014. ETo was calculated using the expected maximum, minimum, and mean Tair according to the Har method and was used with Kc-Sat to estimate ETc-Har. ETo-FPM is used to measure ETc-FPM with Kc-Sat. LST and NDVI have been used to measure the Water Deficiency Index (WDI). WDI incorporated ETc to measure the actual evapotranspiration of the crop (ETa). ETa-FPM was used for the evaluation of ETa-Har. The relationship between ETa-FPM and ETa-Har was high, where R2 was 0.99 in 2013 and 2014. ETa determined by Hargreaves based on remotely sensed data was overestimated at about 0.8 (mm/day) compared to the FPM process.

Optimal timing of fungicide applications on maize, soybean, and beans based on calendar and agrometeorological data

ABSTRACT The objective of this study was to determine the best method to establish optimal timing of fungicide applications on corn (Zea mays), soybean (Glycine max), and bean plants (Phaseolus vulgaris), by comparing results based on the calendar versus agrometeorological data. The experimental design was arranged in randomised blocks with three treatments and eight repetitions. Treatments consisted of control (without application of fungicides), application of fungicides based on the calendar (after establishing the need for chemical control, sprays occurring at intervals of 15 days), or by indication of the AgroDetecta™ programme (based on agrometeorological data). The variables evaluated were: disease incidence and severity, area under the disease progress curve (AUDPC), income components, and economic return. Among the integrated disease management tools investigated, it was concluded that chemical control improves crop health and yield for corn, soybean, and bean plants, especially when timing of treatment application is based on the calendar. The programme AgroDetecta™ showed promise as a decision-making tool for the best timing to spray, but requires adjustments for commercial use.

Evaluation of Different Modelling Techniques with Fusion of Satellite, Soil and Agro-Meteorological Data for the Assessment of Durum Wheat Yield under a Large Scale Application

Food and feed production must be increased or maintained in order to meet the demands of the earth’s population. Under this scenario, the question that arises is how to address the demand for agricultural products given that the pressures on land use have already increased. In addition, it is obvious that climate change will have a serious negative impact and threaten the productivity and sustainability of food production systems. Therefore, understanding and predicting the outcome of crop production, while considering adaptation and sustainability, is essential. The need for information on decision making at all levels, from crop management to adaptation strategies, is constantly increasing and methods for providing such information are urgently needed in a relatively short period of time. Thus arises the need to use effective data, such as satellite and meteorological data, but also operational tools, to assess crop yields over local, regional, national, and global scales. In this work, three modeling approaches built on a fusion of satellite-derived vegetation indices, agro-meteorological indicators, and crop phenology are tested and evaluated in terms of data intensiveness for the prediction of wheat yields in large scale applications. The obtained results indicated that medium input data intensity methods are effective tools for yield assessments. The methods, namely, a semi-empirical regression model, a machine learning regression model, and a process-based model, provided high to moderate accuracies by fully relying on freely available datasets as sources of input data. The findings are comparable with those reported in the literature for detailed field experiments, thereby introducing a promising framework that can support operational platforms for dynamic yield forecasting, operating at the administrative or regional unit scale.

Monitoring System of the Mar Menor Coastal Lagoon (Spain) and Its Watershed Basin Using the Integration of Massive Heterogeneous Data.

The tool created aims at the environmental monitoring of the Mar Menor coastal lagoon (Spain) and the monitoring of the land use of its watershed. It integrates heterogeneous data sources ranging from ecological data obtained from a multiparametric oceanographic sonde to agro-meteorological data from IMIDA’s network of stations or hydrological data from the SAIH network as multispectral satellite images from Sentinel and Landsat space missions. The system is based on free and open source software and has been designed to guarantee maximum levels of flexibility and scalability and minimum coupling so that the incorporation of new components does not affect the existing ones. The platform is designed to handle a data volume of more than 12 million records, experiencing exponential growth in the last six months. The tool allows the transformation of a large volume of data into information, offering them through microservices with optimal response times. As practical applications, the platform created allows us to know the ecological state of the Mar Menor with a very high level of detail, both at biophysical and nutrient levels, being able to detect periods of oxygen deficit and delimit the affected area. In addition, it facilitates the detailed monitoring of the cultivated areas of the watershed, detecting the agricultural use and crop cycles at the plot level. It also makes it possible to calculate the amount of water precipitated on the watershed and to monitor the runoff produced and the amount of water entering the Mar Menor in extreme events. The information is offered in different ways depending on the user profile, offering a very high level of detail for research or data analysis profiles, concrete and direct information to support decision-making for users with managerial profiles and validated and concise information for citizens. It is an integrated and distributed system that will provide data and services for the Mar Menor Observatory.

Comparing the use of ERA5 reanalysis dataset and ground-based agrometeorological data under different climates and topography in Italy

Study regionThe study region is represented by seven irrigation districts distributed under different climate and topography conditions in Italy. Study focusThis study explores the reliability and consistency of the global ERA5 single levels and ERA5-Land reanalysis datasets in predicting the main agrometeorological estimates commonly used for crop water requirements calculation. In particular, the reanalysis data was compared, variable-by-variable (e.g., solar radiation, Rs; air temperature, Tair; relative humidity, RH; wind speed, u10; reference evapotranspiration, ET0), with in situ agrometeorological observations obtained from 66 automatic weather stations (2008–2020). In addition, the presence of a climate-dependency on their accuracy was assessed at the different irrigation districts. New hydrological insights for the regionA general good agreement was obtained between observed and reanalysis agrometeorological variables at both daily and seasonal scales. The best performance was obtained for Tair, followed by RH, Rs, and u10 for both reanalysis datasets, especially under temperate climate conditions. These performances were translated into slightly higher accuracy of ET0 estimates by ERA5-Land product, confirming the potential of using reanalysis datasets as an alternative data source for retrieving the ET0 and overcoming the unavailability of observed agrometeorological data.

Tendency for change of agroclimatic conditions for formation of millet yield by 2050 within the Steppe zone of Ukraine

The current trend of climate change requires a significant revision of the species and breed composition of agricultural crops. Preference should be given to drought-resistant crops such as millet, especially in the Steppe zone of Ukraine. Thus studies of agro-climatic conditions for formation of millet yields in the coming years are of great importance. The article covers the assessment of changes in agro-climatic resources for the northern and Southern Steppe zones of Ukraine according to RCP4.5 and RCP8.5 scenarios during three ten-year periods: 2021-2030, 2031-2040 and 2041-2050 as compared with the basic period of 1986-2005. The research applies the basic model for assessment of agro-climatic resources of formation of agricultural crops productivity developed by A. M. Polevoy. The model uses meteorological and agrometeorological data of air temperature and humidity, precipitation, solar radiation, water-physical properties and soil moisture obtained through standard meteorological and agrometeorological observations. The model of crops production process allowed establishing the agro-climatic resources during millet vegetation season and indicators of photosynthetic productivity, as well as determining the regularities for formation of different agri-environmental categories of crop yield and crop yield fluctuations under climate change within the thirty-year period from 2021 to 2050. The research evaluates the change of aforementioned indicators both in the context of individual periods and in the context of the Northern and Southern Steppe zones. It was found that the largest change in agro-climatic resources and millet productivity is observed in the Southern Steppe zone. For both the Southern and Northern Steppe zones the largest difference of such indicators is observed under the RCP8.5 climate change scenario. It was also found that the largest change of the indicators is observed within the period from 2031 to 2040. However, within the next decade, the values of all indicators will be close to the data observed during the basic period (1986-2005). According to the results of calculations for the period from 2021 to 2050 under RCP4.5 and RCP8.5 scenarios the expected scenario yields will be higher than those of the basic period.

Influence of climate stress on technical efficiency and economic downside risk exposure of EU dairy farms

AbstractThis paper assesses the influence of heat and drought stress on the economic performance of the European dairy sector. Climatic data from the Gridded Agro-Meteorological data in Europe were combined with dairy enterprise data from the Farm Accountancy Data Network, resulting in a data set of 4412 farms in 22 European Union (EU) countries over the period 2007–2013. Since the performance of dairy farms is influenced by the context in which they operate, farms were grouped into areas representing similar climatic conditions through the use of a latent class analysis. Technical efficiency (TE) and economic downside risk were used as performance indicators against which the effect of climatic stress factors was evaluated. TE was estimated using a ‘true-fixed’ effect stochastic frontier model. Economic downside risk was based on gross margin deviations. Regression analysis suggests a significant negative effect of drought and heat stress on both TE and the downside gross margin difference in most climatic classes, with few exceptions. Results imply that both drought and heat stress-related issues need to be considered when designing adaptation strategies to address threats to the economic performance of the EU dairy sector.

Assessment of Farmers' Adoption Level of Climate Change Adaptation Practices in the Southern Parts of Tamil Nadu

Climate change is a global hazard to the world's food and nutritional security. As greenhouse-gas emissions in the atmosphere rise, so does the temperature due to the greenhouse effect. The average world temperature is steadily rising and is expected to climb by 2 degrees Celsius by 2100, resulting in significant global economic losses. Climate variability in the form of temperature and precipitation may impact on agricultural production and productivity. The study was conducted in the wetland, dryland, and garden land farming systems of the Tamil Nadu districts of Madurai and Sivagangai with a sample size of 120 farmers. Descriptive statistics were used in this study. For compare all three systems; a simple percentage analysis was performed. The majority of respondents in the wetland (65.00%), dryland (70.00%), and garden land (75.00%) farming reported a medium level of climate change adaptations. Cropping system diversification includes mixed cropping (65.00%), intercropping (36.66%), perennial and tree crop agriculture (30.00%), and fallow cropping (25.8%). Summer ploughing (36.67%) and micro-irrigation systems (34.17%) were among the water conservation strategies used by nearly one-third of those polled. The majority of respondents (85.00%) were rearing cattle followed by working as a r worker (off-farm activities) (56.67%) in the local industry is the second most common income diversification activity done by farmers.Government and agencies must play an important role in improving farmers' adaptive capacity by disseminating agrometeorological data and tools, conducting vulnerability assessments, and providing policy advice to strengthen institutional approaches to disaster risk reduction so that farmers can respond to the immediate risks of climate change and make the best use of climate variability.

Prediction of Oil Palm Yield Using Machine Learning in the Perspective of Fluctuating Weather and Soil Moisture Conditions: Evaluation of a Generic Workflow.

Current development in precision agriculture has underscored the role of machine learning in crop yield prediction. Machine learning algorithms are capable of learning linear and nonlinear patterns in complex agro-meteorological data. However, the application of machine learning methods for predictive analysis is lacking in the oil palm industry. This work evaluated a supervised machine learning approach to develop an explainable and reusable oil palm yield prediction workflow. The input data included 12 weather and three soil moisture parameters along with 420 months of actual yield records of the study site. Multisource data and conventional machine learning techniques were coupled with an automated model selection process. The performance of two top regression models, namely Extra Tree and AdaBoost was evaluated using six statistical evaluation metrics. The prediction was followed by data preprocessing and feature selection. Selected regression models were compared with Random Forest, Gradient Boosting, Decision Tree, and other non-tree algorithms to prove the R2 driven performance superiority of tree-based ensemble models. In addition, the learning process of the models was examined using model-based feature importance, learning curve, validation curve, residual analysis, and prediction error. Results indicated that rainfall frequency, root-zone soil moisture, and temperature could make a significant impact on oil palm yield. Most influential features that contributed to the prediction process are rainfall, cloud amount, number of rain days, wind speed, and root zone soil wetness. It is concluded that the means of machine learning have great potential for the application to predict oil palm yield using weather and soil moisture data.