Agricultural Systems Research Articles

Smart technology-based microclimate control system for greenhouse

This study proposes an agricultural management system designed to enhance productivity by leveraging artificial intelligence and Internet of Things (IoT) technologies. It addresses the complex microclimate conditions within greenhouses by integrating microcontrollers and sensors to monitor parameters such as temperature, humidity, and soil moisture, enabling precise environmental management. Web and mobile applications provide interactive interfaces, allowing users to monitor real-time factors influencing the greenhouse environment. The system can execute actions like activating fans or irrigation pumps based on user inputs or predefined settings. In addition to improving yields, the system aims to create a dataset that can be used for assessing the effectiveness of future machine learning models. Important considerations include data privacy, training farmers to effectively use the technology, and integrating the system with traditional farming practices, thereby enhancing sustainability. Overall, this study aspires to continuously improve agricultural practices by combining modern technology with traditional knowledge, ultimately aiming for a more efficient and sustainable agricultural landscape.

Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming

AbstractVertical farming (VF) refers to systems of agriculture where crops are grown in trays stacked vertically by exposing them to artificial light and using sensing technology to improve product quality and yield. In this work, we propose an advanced filtering scheme based on recurrent neural networks (RNNs) and deep learning to enable efficient control strategies for VF applications. We demonstrate that the best RNN model incorporates five neuron layers, with the first and second containing 90 long short‐term memory neurons. The third layer implements one gated recurrent units neuron. The fourth segment incorporates one RNN network, while the output layer is designed by using a single neuron exhibiting a rectified linear activation function. By utilizing this RNN digital filter, we introduce two variations: (1) a scaled RNN model to tune the filter to the signal of interest, and (2) a moving average filter to eliminate harmonic oscillations of the output waveforms. The RNN models are contrasted with conventional digital Butterworth, Chebyshev I, Chebyshev II, and elliptic infinite impulse response (IIR) configurations. The RNN digital filtering schemes avoid introducing unwanted oscillations, which makes them more suitable for VF than their IIR counterparts. Finally, by utilizing the advanced features of scaling of the RNN model, we demonstrate that the RNN digital filter can be pH selective, as opposed to conventional IIR filters.

Mapping Soil Surface Moisture of an Agrophytocenosis via a Neural Network Based on Synchronized Radar and Multispectral Optoelectronic Data of SENTINEL-1,2—Case Study on Test Sites in the Lower Volga Region

In this article, the authors developed a novel method for the moisture mapping of the soil surface of agrophytocenosis using a neural network based on synchronized radar and multispectral optoelectronic data from Sentinel-1,2. The significance of this research lies in its potential to enhance precision farming practices, which are increasingly vital in addressing global agricultural challenges such as water scarcity and the need for sustainable resource management. To verify the developed method, data from two experimental plots were utilized. These plots were located on irrigated soybean crops, with the first plot situated on the right bank (plot No. 1) and the second on the left bank (plot No. 2) of the lower Volga River. Two experimental soil moisture geodatasets were created through measurements and geo-referencing points using the gravimetric method (for plot No. 1) and the proximal sensing method (for plot No. 2) employing the Soil Moisture Sensor ML3-KIT (THETAKIT, Delta). The soil moisture retrieval algorithm was based on the use of a neural network to predict the reflection coefficient of an electro-magnetic wave from the soil surface, followed by inversion into soil moisture using a dielectric model that takes into account the soil texture. The input parameter of the neural network was the ratio of the microwave radar vegetation index (calculated based on Sentinel-1 data) to the index (calculated based on the data of multispectral optoelectronic channels 8 and 11 of Sentinel-2). The retrieved soil moisture values were compared with in situ measurements, showing a determination coefficient of 0.44–0.65 and a standard deviation of 2.4–4.2% for plot No. 1 and similar metrics for plot No. 2. The conducted research laid the groundwork for developing a new technology for remote sensing of soil moisture content in agrophytocenosis, serving as a crucial component of precision farming systems and agroecology. The integration of this technology promotes sustainable agricultural practices by minimizing water consumption while maximizing crop productivity. This aligns with broader environmental goals of conserving natural resources and reducing agricultural runoff. On a larger scale, data derived from such studies can inform policy decisions related to water resource management, guiding regulations that promote efficient water use in agriculture.

Energy Efficiency and Mathematical Modeling of Shrimp Pond Oxygenation: A Multiple Regression Experimental Study

Aquaculture is one of the key economic activities to reduce food shortages worldwide. Water recirculation systems using pumps are crucial to maintain oxygenation and water quality, consuming about 35% of the total energy in this economic activity. This research proposes a multiple linear regression mathematical model to optimize oxygenation systems in intensive shrimp aquaculture by reducing energy consumption and minimizing water changes in ponds. The proposed model is key to optimizing the operation of pumping systems, allowing us to significantly reduce water turnover without compromising dissolved oxygen levels as a function of key variables such as water turnover volume, biomass, solar radiation (0–1200 W/m2), water temperature (20 °C–32 °C), phytoplankton levels (0–1,000,000 cells/ml), zooplankton (0–500,000 cells/ml), and wind speed (0–15 m/s). These variables are integrated into the model, managing to explain 94.02% of the variation in dissolved oxygen, with an R2 of 92.9%, which adjusts the system conditions in real time, reducing the impact of environmental fluctuations on water quality. This leads to an estimated annual energy savings of 106,397.5 kWh, with a total consumption of 663.8 MWh. The research contributes to the development of a mathematical approach that not only improves oxygenation prediction, but also minimizes the use of water resources, improving the sustainability and profitability of shrimp farming systems, and is a robust tool that maximizes operational efficiency in intensive aquaculture, particularly where water and energy management are critical.

Applicability of soil health assessment dominated by biological indicators in facility agriculture

The minimum data set (MDS) is widely used for soil health index (SHI) assessment, with the selection of indicators being crucial. However, biological indicators are less frequently used compared to physical and chemical indicators. This study aimed to establish a biologically-centered MDS for assessing soil health in tomato facility agriculture in Ningbo. Using biochemical, microbiological, and nematode data from 60 continuous cropping soils, we identified key indicators for the MDS. Principal component analysis revealed a strong correlation between the MDS and the total data set (TDS), with the final MDS including available phosphorus, electrical conductivity, β-glucosidase, urease, bacterial Chao1 index, bacterial Shannon index, Ralstonia solanacearum, nematode Shannon index, structure index, and channel index. Random forest modeling showed that the predicted SHI had a high fit with the MDS-SHI, with bacterial and nematode Shannon indices being the most influential predictors, emphasizing the critical role of biological communities in maintaining soil health. Furthermore, the study identified three distinct phases in soil health during long-term continuous cropping: healthy (0–10 years), sub-healthy (11–15 years), and recovery (16–20 years), demonstrating the soil's potential for self-recovery. By incorporating biodiversity as a core component, this biologically-focused MDS provides a more comprehensive and precise method for evaluating soil health in facility agriculture. The findings suggest that this MDS could inform future research and applications in similar agricultural systems. Moreover, the results highlight the vital role of biodiversity in agroecosystem stability, suggesting that future soil health assessments should place greater emphasis on biological indicators to better capture the complexity of soil functions.

Responses of Legumes to Rhizobia and Arbuscular Mycorrhizal Fungi Under Abiotic Stresses: A Global Meta-Analysis

Arbuscular mycorrhizal fungi (AMF) and rhizobia play a pivotal role in enhancing crop productivity, shaping microbial community structure, and improving soil quality, making them key components for sustainable ecosystem development. The symbiotic relationship between AMF and rhizobia is crucial for facilitating efficient biological nitrogen fixation and nutrient absorption, thereby reducing the dependence on chemical fertilizers and promoting sustainable agricultural practices. The findings of various studies, however, indicate that soil environment can impede the symbiotic relationship between AMF and rhizobia. We conducted a comprehensive meta-analysis of 158 articles from 1980 to 2022 to explore the synergistic interactions in legume–AMF–rhizobium systems and the potential mechanisms underlying this synergism. Our findings revealed that the inoculation with AMF and/or rhizobia significantly (p < 0.001) increased legume plant nitrogen content, phosphorus content, shoot biomass, yield, AMF colonization rate, and the number and weight of nodules compared to uninoculated controls (effect size d > 0). Moreover, there was a substantial synergistic effect between AMF and rhizobia (p < 0.001). Nevertheless, soil salinity stress, drought stress, and pH stress could hinder the positive effects of inoculation treatments, possibly due to the plant trade-off strategies under abiotic stress conditions. This research may potentially lead to new solutions for sustainable agricultural systems amidst the challenges posed by global climate change.

Management of soil phosphorous using phosphate solubilizing microorganisms: A sustainable approach

Phosphorus is crucial for plant growth and productivity, and its scarcity in soil negatively affects crop yields. A major portion of chemical phosphate fertilizer precipitates with soil minerals, making it unavailable for plant growth. Phosphate-solubilizing microorganisms play a pivotal role in enhancing phosphorus availability, facilitating better nutrient absorption, and ultimately boosting plant growth. This article presents a brief overview of the phosphorus status in Indian soil, discusses the various forms of phosphorus and its dynamics across different soil types, and analyses the factors involved, highlighting the importance of phosphorus management for sustainable agriculture. Physiological and molecular mechanisms of microbial phosphate solubilization provide deep insights into exploring PSMs for managing phosphorous in different soil types. It also provides a path for the necessity to explore the multifarious plant growth-promoting traits of PSMs underscoring its applicability for sustainable agricultural practices with viable economy. The mechanism of solubilization of phosphorus has been discussed to understand the role of microorganisms in different soils. The study highlights the role of significant microorganisms in developing tailored consortia of PSMs and other plant growth-promoting rhizobacteria (PGPR) based on the chemical composition of the soil, along with an integrated nutrient approach incorporating PSMs. This review offers valuable insights into harnessing PSMs and their practical applications, facilitating their broader adoption in agricultural systems to maintain soil health.

Growth regulation in bread wheat via novel bioinoculant formulation

Wheat (Triticum aestivum L.) is one of the most significant crops and the backbone of food security worldwide. However, low wheat production remains a substantial concern in global agricultural systems. It can be attributed to several factors, including adverse climatic conditions, plant disease and poor soil quality. Recent efforts have explored bioinoculant applications as a promising approach to enhance wheat yield, trying to mitigate constraints essential for future wheat production and global food security. This study tested talc powder, wheat biochar, sugarcane bagasse biochar, and farmyard manure as carriers with two endophytic bacterial strains, Burkholderia phytofirmans PsJN and Bacillus spp. MN54 was applied to three wheat varieties (Ujala-16, Zincol-16, and Fathejang-16). The data was recorded at the seedling and maturity growth stages of plants. A pot experiment revealed significant improvements in plant growth following bioinoculant application compared to controls. Notably, the combination of sugarcane bagasse biochar with Bacillus sp. MN54 exhibited the most pronounced effects, promoting internodal length, spike length, tiller number per plant, grain yield per plant, and spikelets per spike. Additionally, talc powder with Bacillus sp. MN54 increased peduncle length, tiller number per plant, and spike length in Fathejang-16. These findings offer valuable insights into optimizing bioinoculant formulations for improved agricultural practices, adapting to climate change, and contributing to ensuring global food security.

Phosphorus lability in a Ferralsol as affected by land-use change in the Brazilian Cerrado

ABSTRACT Low availability of phosphorus (P) is a constraint to agricultural development in tropical soils, owing to the high fixation of P in the soil matrix. Land-use change can modify soil P dynamics. This study aimed to evaluate the effects of land-use change on P fractions in a Ferralsol under different systems of use and management. Inorganic (Pi) and organic soil P (Po) fractions were assessed by sequential fractionation using H2O, NaHCO3, NaOH, hot concentrated HCl and H2SO4-H2O2 as extractants. The systems in the study were as follows: pasture (PAST), no-tillage system (NT), organic cultivation (ORG) with 2, 6, 8 and 10 years of organic management, and conventional continuous cropping tillage (CT). A native Cerrado forest (F) area was used as reference. In general, Po forms predominated over Pi, with exception of the CT soil, where Pi represented 41% of the total P. On average, conversion of F into the CT system reduced levels of Po in the soil by up to 72%. The soil P resilience index showed that P inputs in the CT and NT systems were insufficient at recovering P availability after the land-use change. On the other hand, the most recent ORG systems demonstrated the greatest efficiency at restoring the equilibrium of the soil P state. The hypothesis that less intensive agricultural systems increase the soil labile P pool, enhancing available P levels, was confirmed. Agricultural systems that used organic inputs and reduced soil disturbance were found to be more efficient at recovering and maintaining soil P availability.

Easy yield mapping for precision agriculture

ABSTRACT Within precision agriculture, yield mapping is important in the evaluation of crop management and delineation of management zones. It can also be used to assess within-field yield potential, in order to guide different precision agriculture practices. However, some farmers do not have a yield monitoring system, and some who do may obtain incomplete or erroneous yield data. This study examined the accuracy with which winter wheat (Triticum aestivum L.) yield could be mapped in 18 fields in southern Sweden using a simple empirical relationship between Sentinel-2 (ESA, Paris, France) data, vegetation index (VI) maps and combined harvester data collected in nearby fields. The results showed that a decrease in map resolution to 40 m reduced the error in the yield maps obtained. Normalised difference water index (NDWI) was the most efficient VI, while a combination of satellite data from earlier and later plant development (booting and milk development stages) performed slightly better than data for other development stages and combinations. The best-performing model at a within-field scale (40-m resolution) had an average mean absolute error (MAE) of 0.40 tonnes ha−1 in a leave-one-field-out cross validation. When the prediction model at field-means scale was applied on 69 farms in a 1055 km2 area, MAE was 0.75 tonnes ha−1 when comparing predictions with mean yields reported by farmers in a phone survey. Therefore, if adequate combined harvester and/or mean yield data are available, a modelling framework that translates satellite imagery into yield maps on-the-fly could be made available for different stakeholders via decision support systems for precision agriculture.

Women's dietary diversity is associated with homestead production and market access: A cross-sectional study in rural Rwanda.

Dietary diversity has been widely used as a proxy indicator for micronutrient adequacy. In low- and middle-income countries (LMICs), including Rwanda, women are at high risk of inadequate micronutrient intake resulting from poorly diversified diets. This study was conducted to examine the factors associated with women's dietary diversity, with emphasis on homestead production diversity and market access in the Northern Province of Rwanda. A cross-sectional design was used, involving 606 women aged 18-49 years. Linear regression analyses were performed to examine the association between various factors and women's dietary diversity. Results show that 84% of the sample households raised at least one livestock species. Seventy-one percent of the households had no agricultural land. Eighty percent of those without land had a homestead garden on which they grew food crops, mainly vegetables and fruit trees. The average crop species was 2.3. On average, women consumed 3 out of 9 food groups. The homestead production diversity score was positively associated with women's dietary diversity score (β = 0.16, p < 0.001). Women's dietary diversity score was negatively associated with distance from the household to the nearest market (β = -0.08, p = 0.027) and household food insecurity (β = -0.06, p < 0.001). Maternal education (p < 0.001), household wealth index (p < 0.05), and ownership of more than 2.5 acres compared to being without land (p < 0.05) were associated with women's dietary diversity score. The dietary diversity of women could be enhanced through interventions that promote the diversity of livestock and crop species produced through homestead production. Potential interventions to explore may include integrated farming systems that combine small livestock and crop production utilising improved livestock breeds and high-quality seeds and planting materials of high-yielding varieties of fruits and vegetables, along with rainwater harvesting to facilitate small-scale irrigation. The impact of such interventions on women's dietary diversity can be further reinforced by parallel programmes aimed at improving women's education and the socioeconomic status of households.

Soil Acidification and Its Temporal Changes in Tea Plantations of Guizhou Province, Southwest China

ABSTRACTSoil acidification is a significant problem in intensive agricultural systems, particularly in tea plantations. Guizhou province, located in the center of the karst mountainous region of southwest China, has the largest tea plantation area in China. However, the soil acidification characteristics in the tea plantations of Guizhou province, as well as their temporal changes, have not yet been adequately studied. Therefore, soil acidification and associated soil properties in the major tea‐planting counties of Guizhou province were extensively assessed, and the temporal changes in soil acidity over the past 11 years were also evaluated through long‐term and short‐term experiments. The results showed that the average soil pH in the tea plantations in Guizhou province varied from 4.08 to 4.87, with a mean of 4.47. The average cation exchange capacity (CEC), TEA (total exchangeable acidity, TEA), EH (exchangeable H+), and EA (exchangeable Al3+) values were 9.6, 3.7, 5.8, and 19.0 cmol/kg, respectively. Seasonal changes in tea plantation soil pH were observed in low‐ and moderately acidic soils but not in highly acidic soils. The soil pH values did not significantly change during three consecutive years of in situ observations but significantly decreased over the past 11 years at an average of 0.03 yearly. Correlation analysis revealed that the soil pH in tea plantations was significantly positively correlated with the content of specific amino acids, such as glutamic acid, arginine, and valine, but was significantly negatively correlated with certain soil physicochemical properties. The findings of this study indicate that soil acidification in tea plantations of the Guizhou province is severe and possesses distinctive attributes that should be considered for its effective management.

An evaluation of soil carbon models and their role on finding ways to net-zero carbon in agricultural systems

The estimation of changes in soil organic carbon (SOC) is a key issue for national green-house gasses (GHG) inventories, climate change mitigation programs and the estimation of carbon footprint of farm products in life cycle assessments. Any strategy related to net-zero carbon in agricultural systems needs to quantify the SOC balance. In this way, SOC models help decision makers involved in agriculture to understand the dynamics of the SOC and the interaction between all variables related to soil, climate, land use, and management, to design the best solution to reduce emissions or enable carbon sequestration. Likewise, it is important to identify suitable models for the region. This study aims to address three main subjects: a) a discussion on the importance of SOC estimation for GHG inventories and the carbon footprint of crops, using the Intergovernmental Panel on Climate Change (IPCC) Tier 1 method and AMG model; b) an evaluation and brief description of the IPCC “Steady State Method” (SSM), using experimental data from two sites in Argentina, comparing these results to AMG and RothC models (both previously validated at those sites); and c) a brief discussion about the potential use of SOC models for what-if management scenarios, their real limitations and future research needs. The three models were consistent in predicting the impact of tillage and the long-term trends in changes in SOC stocks under different management practices. The SSM model was evaluated for the first time in Argentina and performed even better than the other two models. It was consistent with the observed values, when predicting the effect of tillage system under different crop rotations, including pasture systems. Regarding efficiencies of the models, they showed acceptable Nash-Sutcliffe Efficiency (NSE) values, and the root mean square error (RMSE) was also acceptable between 3 % and 7 %, within a range of 4–5 Mg C.ha−1. Therefore, the SSM model proved to be a valuable tool to estimate SOC trends for crop and pasture rotations under different management scenarios (i.e., tillage systems and fertilization), to identify best practices that allow for a zero or positive SOC balance, in two different soil and climate conditions of the Pampean Region of Argentina. In our study, the SSM did have a better fit to the data and, furthermore, this Tier 2 method is simpler than the Tier 3 models, and, therefore, is advantageous for conducting regional assessments and GHG inventories.

ENDOPHYTIC MICROORGANISMS AS BIOCONTROL AGENTS: AN ALTERNATIVE FOR SUSTAINABLE AGRICULTURAL PRODUCTION SYSTEM

Endophytic microorganisms emerge as a sustainable alternative, offering benefits to plants, such as increased resistance to stress and pathogens. This research aims to conduct a literature review on the potential of endophytic microorganisms in the biological control of pathogens in agricultural systems, as a sustainable alternative to traditional methods. Endophytes can act directly on insects or colonize plants, creating a natural defense against pests. They also show promise in the control of phytopathogens, helping to reduce the use of chemical fungicides and encouraging more sustainable agricultural practices, producing bioactive compounds with effective antifungal activity against pathogens. In addition, they show potential as natural herbicides, negatively affecting the germination and development of weeds. Although more research is needed on the potential of endophytes in agricultural systems, they show great promise for more sustainable management.

Chinese Patent Review of Integrated Management System for Agricultural Machinery

Background: With the rapid development of China's economy and the accelerating process of agricultural mechanization, agricultural machinery has become increasingly popular in agricultural production activities. At the same time, problems in agricultural machinery management have gradually been exposed, hindering the development of modern agriculture. Objective: This study aimed to discuss the development trend of agricultural management and modern agriculture by analyzing and discussing the related patents of agricultural machinery management systems. Methods: The development of agricultural machinery management was summarized, and the representative patents related to agricultural machinery management systems, agricultural machinery automatic control systems, and agricultural machinery terminals were analyzed. Results: By analyzing the existing patents of the agricultural machinery management system, the paper summarized their applications in agricultural management and obtained their future development trend. Conclusion: In agricultural machinery management, we should actively adopt complementary strategies to solve various problems and improve the management level of agricultural machinery. The continuous improvement of the agricultural machinery management system is of great significance to the automation of agricultural production and the modernization of agricultural management in China.

Agricultural carbon credits: A pathway to environmental sustainability

Climate change and ensuring food security for a rapidly growing global population are two of the biggest challenges in agriculture. To meet the commitments made in the Paris Climate Agreement, it is important to use effective methods for managing soil that can help sequester and stabilise carbon. Conservation agriculture has a huge potential to sequester carbon in plants and soil, making it a viable option for carbon trading despite its significant contribution to global greenhouse gas emissions. Carbon sequestration can be achieved through sustainable practices such as adopting conservation agriculture, crop rotation, cover crop cultivation, crop residue incorporation or mulching, effective management of nutrient supply to crops, and transforming towards organic agriculture and agroforestry. These practices promote food security and environmental improvement and help mitigate global warming. Carbon pricing mechanisms are policies that impose a cost on carbon pollution, encouraging people and organisations to choose low-carbon options and reduce their emissions. Agricultural producers can benefit from carbon trading by earning extra revenue by selling their excess carbon credits to those who emit higher amounts of greenhouse gases. Carbon credit systems in agriculture are still in the early stages, so farmers may have more opportunities to participate in future carbon trading.

Using Marker-Assisted Selection to Develop a Drought-Tolerant Rice Line with Enhanced Resistance to Blast and Brown Planthopper

Rice is a major global staple crop, but rising temperatures and freshwater shortages have made drought one of the most severe abiotic stresses affecting agriculture. Additionally, rice blast disease and brown planthopper infestations significantly impact yields. Therefore, developing water-saving, drought-resistant, high-yielding, and disease-resistant rice varieties is critical for sustainable rice production. The new water-saving and drought-resistant (WDR) rice ‘Huhan 1516’, bred using marker-assisted selection (MAS) and marker-assisted backcrossing (MABC) techniques, addresses these challenges. This variety is highly adaptable to drought-prone and water-scarce regions such as the Yangtze and Huai River basins. With its high yield, drought tolerance, and broad-spectrum resistance to rice blast (conferred by the Pi2 gene) and brown planthopper (BPH), ‘Huhan 1516’ is suitable for various farming systems and environments. Field trials show that this variety outperforms control varieties by 2.2% in yield and exhibits moderate resistance to both rice blast and brown planthopper. ‘Huhan 1516’ has been recognized as a new water-saving and drought-resistant rice variety by the state, and as a released cultivar, it has great potential for market promotion and application.

Tetracycline resistance gene transfer from Escherichia coli donors to Salmonella Heidelberg in chickens is impacted by the genetic context of donors

Chicken ceca are a rich source of bacteria, including zoonotic pathogens such as Salmonella enterica. The microbiota includes strains/species carrying antimicrobial resistance genes and horizontal transfer of resistance determinants between species may increase the risk to public health and farming systems. Possible sources of these antimicrobial resistance donors – the eggshell carrying bacteria from the hen vertically transmitted to the offspring, or the barn environment where chicks are hatched and raised – has been little explored. In this study, we used Salmonella enterica serovar Heidelberg to evaluate if layer chicks raised in different environments (using combinations of sterilized or non-sterile eggs placed in sterilized isolation chambers or non-sterile rooms) acquired transferable tetracycline resistance genes from surrounding bacteria, especially Escherichia coli. Two-day old chicks were challenged with an antibiotic-susceptible S. Heidelberg strain SH2813nalR and Salmonella recovered from the cecum of birds at different timepoints to test the in vivo acquisition of tetracycline resistance. Tetracycline-resistant E. coli isolates recovered from birds from the in vivo experiment were used to test the in vitro transfer of tetracycline resistance genes from E. coli to Salmonella. Even though Salmonella SH2813nalR colonized the 2-day old chicks after oral challenge, tetracycline-resistant Salmonella transconjugants were not recovered, as previously observed. In vitro experiments provided similar results. We discuss several hypotheses that might explain the absence of transconjugants in vitro and in vivo, despite the presence of diverse plasmids in the recovered E. coli. The factors that can inhibit/promote antimicrobial resistance transfers to Salmonella for different plasmid types need further exploration.

Assessing forecast performance of daily reference evapotranspiration: A comparison of equations, machine and deep learning using weather forecasts

An accurate forecast of short-term reference evapotranspiration (ET0) is crucial for effective farm and irrigation scheduling management. The techniques of forecasting ET0 have progressed from empirical equations to artificial intelligence-based models. However, gaps have remained in comprehensively evaluating the ET0 forecast performance discrepancies between various methods based on weather forecasts in addition to historical meteorological data, as well as investigating the effect of the amount of input variables on ET0 forecast accuracy. Here, the study evaluated the forecast accuracy of five conventional equations calibrated and six machine learning (ML) and deep learning (DL) models in predicting daily ET0 for a lead time of 1–7 days in the North China Plain (NCP). Comparative evaluations indicate that the Analytical Penman-Monteith (APM) is the optimum empirical equation for forecasting ET0, but its accuracy decreases as lead times increase. Conversely, ML and DL models consistently outperform empirical equations, characterized by lower mean absolute error (MAE) and root mean square error (RMSE) as well as correlation coefficient and Nash-Sutcliffe efficiency coefficient approaching 1 across all lead times. Notably, the Bidirectional Long short-term memory (Bi-LSTM) model outperforms other models, maintaining robust and effective forecast performance even on day 7. Moreover, with the increasing input variables, combining weather forecasts and historical meteorological data, the forecast performance of all models is improved, with significant enhancement observed in the Bi-LSTM model. This work provides valuable insights for choosing appropriate models to forecast ET0, holding essential in regional managing farm and irrigation systems.

Agricultural land-use system management: research progress and perspectives

Agricultural land-use system management: research progress and perspectives