Towards deep learning based smart farming for intelligent weeds management in crops.

Introduction: Deep learning (DL) is a core constituent for building an object detection system and provides a variety of algorithms to be used in a variety of applications. In agriculture, weed management is one of the major concerns, weed detection systems could be of great help to improve production. In this work, we have proposed a DL-based weed detection model that can efficiently be used for effective weed management in crops. Methods: Our proposed model uses Convolutional Neural Network based object detection system You Only Look Once (YOLO) for training and prediction. The collected dataset contains RGB images of four different weed species named Grass, Creeping Thistle, Bindweed, and California poppy. This dataset is manipulated by applying LAB (Lightness A and B) and HSV (Hue, Saturation, Value) image transformation techniques and then trained on four YOLO models (v3, v3-tiny, v4, v4-tiny). Results and discussion: The effects of image transformation are analyzed, and it is deduced that the model performance is not much affected by this transformation. Inferencing results obtained by making a comparison of correctly predicted weeds are quite promising, among all models implemented in this work, the YOLOv4 model has achieved the highest accuracy. It has correctly predicted 98.88% weeds with an average loss of 1.8 and 73.1% mean average precision value. Future work: In the future, we plan to integrate this model in a variable rate sprayer for precise weed management in real time.

A mobile-based system for maize plant leaf disease detection and classification using deep learning.

Artificial Intelligence has been used for many applications such as medical, communication, object detection, and object tracking. Maize crop, which is the major crop in the world, is affected by several types of diseases which lower its yield and affect the quality. This paper focuses on this issue and provides an application for the detection and classification of diseases in maize crop using deep learning models. In addition to this, the developed application also returns the segmented images of affected leaves and thus enables us to track the disease spots on each leaf. For this purpose, a dataset of three maize crop diseases named Blight, Sugarcane Mosaic virus, and Leaf Spot is collected from the University Research Farm Koont, PMAS-AAUR at different growth stages on contrasting weather conditions. This data was used for training different prediction models including YOLOv3-tiny, YOLOv4, YOLOv5s, YOLOv7s, and YOLOv8n and the reported prediction accuracy was 69.40%, 97.50%, 88.23%, 93.30%, and 99.04% respectively. Results demonstrate that the prediction accuracy of the YOLOv8n model is higher than the other applied models. This model has shown excellent results while localizing the affected area of the leaf accurately with a higher confidence score. YOLOv8n is the latest model used for the detection of diseases as compared to the other approaches in the available literature. Also, worked on sugarcane mosaic virus using deep learning models has also been reported for the first time. Further, the models with high accuracy have been embedded in a mobile application to provide a real-time disease detection facility for end users within a few seconds.

Research hotspots and frontiers in agricultural multispectral technology: Bibliometrics and scientometrics analysis of the Web of Science.

Multispectral technology has a wide range of applications in agriculture. By obtaining spectral information during crop production, key information such as growth, pests and diseases, fertilizer and pesticide application can be determined quickly, accurately and efficiently. The scientific analysis based on Web of Science aims to understand the research hotspots and areas of interest in the field of agricultural multispectral technology. The publications related to agricultural multispectral research in agriculture between 2002 and 2021 were selected as the research objects. The softwares of CiteSpace, VOSviewer, and Microsoft Excel were used to provide a comprehensive review of agricultural multispectral research in terms of research areas, institutions, influential journals, and core authors. Results of the analysis show that the number of publications increased each year, with the largest increase in 2019. Remote sensing, imaging technology, environmental science, and ecology are the most popular research directions. The journal Remote Sensing is one of the most popular publishers, showing a high publishing potential in multispectral research in agriculture. The institution with the most research literature and citations is the USDA. In terms of the number of papers, Mtanga is the author with the most published articles in recent years. Through keyword co-citation analysis, it is determined that the main research areas of this topic focus on remote sensing, crop classification, plant phenotypes and other research areas. The literature co-citation analysis indicates that the main research directions concentrate in vegetation index, satellite remote sensing applications and machine learning modeling. There is still a lot of room for development of multi-spectrum technology. Further development can be carried out in the areas of multi-device synergy, spectral fusion, airborne equipment improvement, and real-time image processing technology, which will cooperate with each other to further play the role of multi-spectrum in agriculture and promote the development of agriculture.

Twenty-first century hydrologic and climatic changes over the scarcely gauged Jhelum river basin of Himalayan region using SDSM and RCPs.

Climatic and hydrological changes of the scarcely gauged mountainous basins remain a challenge to study due to unavailability of observed data. The recent study aims to assess these changes using spatial decision tool statistical downscaling method (SDSM) and snowmelt runoff model (SRM) for the twenty-first century under representative concentration pathways (RCPs). SDSM considered absolute partial correlation coefficient (abs. Pr.) to evaluate efficiency predictors or the predictands of the Jhelum river basin. The performance evaluation of SDSM assessed using coefficient of determination (R2) values for RCP 4.5 and RCP 8.5 under CMIP5 (CCSM4). The biases of the daily time series downscaled data removed by using mean-based biased correction method (MB-BC). Stream projection carried out using SRM by incorporating MODIS snow product. Statistical parameters R2 and volume difference (Dv %) calculated for accuracy assessment of SRM for the simulated and observed discharge (2001-2018). Streamflow projections for the twenty-first century carried out by SRM using de-biased downscaled data. The R2 indicator of SDSM ranged between 78-81% for temperature and 82-86% for precipitation under RCP 4.5 and RCP 8.5, respectively. The temperature results indicated an increasing trend of 1.5oC and 3.8oC for the twenty-first century under RCP 4.5 and RCP 8.5, respectively. The mean annual precipitation showed a rise of 2-7% while surface runoff projected a rising trend of 3.3-7.4% for RCP-4.5 and RCP-8.5 respectively till the end of the twenty-first century. The study results revealed that Jhelum basin will be wetter and warmer for the twenty-first century as compare to the baseline period. The hydrographs of the river predicted the occurrence of more extreme events in the region for the twenty-first century. These hydrographs may help for better water conservation and management strategies in the Jhelum basin for the twenty-first century.

Applied surface enhanced Raman Spectroscopy in plant hormones detection, annexation of advanced technologies: A review.

Plant hormones are the molecules that control the vigorous development of plants and help to cope with the stress conditions efficiently due to vital and mechanized physiochemical regulations. Biologists and analytical chemists, both endorsed the extreme problems to quantify plant hormones due to their low level existence in plants and the technological support is devastatingly required to established reliable and efficient detection methods of plant hormones. Surface Enhanced Raman Spectroscopy (SERS) technology is becoming vigorously favored and can be used to accurately and specifically identify biological and chemical molecules. Subsistence molecular properties with varying excitation wavelength require the pertinent substrate to detect SERS signals from plant hormones. Three typical mechanisms of Raman signal enhancement have been discovered, electromagnetic, chemical and Tip-enhanced Raman spectroscopy (TERS). Though, complex detection samples hinder in consistent and reproducible results of SERS-based technology. However, different algorithmic models applied on preprocessed data enhanced the prediction performances of Raman spectra by many folds and decreased the fluorescence value. By incorporating SERS measurements into the microfluidic platform, further highly repeatable SERS results can be obtained. This review paper tends to study the fundamental working principles, methods, applications of SERS systems and their execution in experiments of rapid determination of plant hormones as well as several ways of integrated SERS substrates. The challenges to develop an SERS-microfluidic framework with reproducible and accurate results for plant hormone detection are discussed comprehensively and highlighted the key areas for future investigation briefly.

Exploring the Impacts of Genotype-Management-Environment Interactions on Wheat Productivity, Water Use Efficiency, and Nitrogen Use Efficiency under Rainfed Conditions.

Wheat production under rainfed conditions is restrained by water scarcity, elevated temperatures, and lower nutrient uptake due to possible drought. The complex genotype, management, and environment (G × M × E) interactions can obstruct the selection of suitable high yielding wheat cultivars and nitrogen (N) management practices prerequisite to ensure food security and environmental sustainability in arid regions. The agronomic traits, water use efficiency (WUE), and N use efficiencies were evaluated under favorable and unfavorable weather conditions to explore the impacts of G × M × E on wheat growth and productivity. The multi-N rate (0, 70, 140, 210, and 280 kg N ha-1) field experiment was conducted under two weather conditions (favorable and unfavorable) using three wheat cultivars (AUR-809, CHK-50, and FSD-2008) in the Pothowar region of Pakistan. The experiments were laid out in randomized complete block design (RCBD), with split plot arrangements having cultivars in the main plot and N levels in the subplot. The results revealed a significant decrease in aboveground biomass, grain yield, crop N-uptake, WUE, and N use efficiency (NUE) by 15%, 22%, 21%, 18%, and 8%, respectively in the unfavorable growing season (2014-2015) as compared to favorable growing season (2013-2014) as a consequence of less rainfall and heat stress during the vegetative and reproductive growth phases, respectively. FSD-2008 showed a significantly higher aboveground biomass, grain yield, crop N-uptake, WUE, and NUE as compared to other wheat cultivars in both years. Besides, N140 appeared as the most suitable dose for wheat cultivars during the favorable growing season. However, any further increase in N application rates beyond N140 showed a non-significant effect on yield and yield components. Conversely, the wheat yield increased significantly up to 74% from N0 to N70 during the unfavorable growing season, and there was no substantial difference between N70-N280. The findings provide opportunities for maximizing yield while avoiding excessive N loss by selecting suitable cultivars and N application rates for rainfed areas of Pothowar Plateau by using meteorological forecasting, amount of summer rainfall, and initial soil moisture content.

Exploring the prospective of weeds (Cannabis sativa L., Parthenium hysterophorus L.) for biofuel production through nanocatalytic (Co, Ni) gasification.

BACKGROUND: While keeping in view various aspects of energy demand, quest for the renewable energy sources is utmost. Biomass has shown great potential as green energy source with supply of approximately 14% of world total energy demand, and great source of carbon capture. It is abundant in various forms including agricultural, forestry residues, and unwanted plants (weeds). The rapid growth of weeds not only affects the yield of the crop, but also has strong consequences on the environment. These weeds can grow with minimum nutrient input requirements, have strong ability to grow at various soil and climate environments with high value of cellulose, thus can be valuable source of energy production. RESULTS: Parthenium hysterophorus L. and Cannabis sativa L. have been employed for the production of biofuels (biogas, biodiesel and biochar) through nano-catalytic gasification by employing Co and Ni as nanocatalysts. Nanocatalysts were synthesized through well-established sol-gel method. SEM study confirms the spherical morphology of the nanocatalysts with size distribution of 20-50 nm. XRD measurements reveal that fabricated nanocatalysts have pure standard crystal structure without impurity. During gasification of Cannabis sativa L., we have extracted the 53.33% of oil, 34.66% of biochar and 12% gas whereas in the case of Parthenium hysterophorus L. 44% oil, 38.36% biochar and 17.66% of gas was measured. Electrical conductivity in biochar of Cannabis sativa L. and Parthenium hysterophorus L. was observed 0.4 dSm-1 and 0.39 dSm-1, respectively. CONCLUSION: Present study presents the conversion of unwanted plants Parthenium hysterophorus L. and Cannabis sativa L. weeds to biofuels. Nanocatalysts help to enhance the conversion of biomass to biofuel due to large surface reactivity. Our findings suggest potential utilization of unwanted plants for biofuel production, which can help to share the burden of energy demand. Biochar produced during gasification can replace chemical fertilizers for soil remediation and to enhance the crop productivity.

Applications and Prospects of Agricultural Unmanned Aerial Vehicle Obstacle Avoidance Technology in China.

With the steady progress of China's agricultural modernization, the demand for agricultural machinery for production is widely growing. Agricultural unmanned aerial vehicles (UAVs) are becoming a new force in the field of precision agricultural aviation in China. In those agricultural areas where ground-based machinery have difficulties in executing farming operations, agricultural UAVs have shown obvious advantages. With the development of precision agricultural aviation technology, one of the inevitable trends is to realize autonomous identification of obstacles and real-time obstacle avoidance (OA) for agricultural UAVs. However, the complex farmland environment and changing obstacles both increase the complexity of OA research. The objective of this paper is to introduce the development of agricultural UAV OA technology in China. It classifies the farmland obstacles in two ways and puts forward the OA zones and related avoidance tactics, which helps to improve the safety of aviation operations. This paper presents a comparative analysis of domestic applications of agricultural UAV OA technology, features, hotspot and future research directions. The agricultural UAV OA technology of China is still at an early development stage and many barriers still need to be overcome.

Estimation of Dynamic Canopy Variables Using Hyperspectral Derived Vegetation Indices Under Varying N Rates at Diverse Phenological Stages of Rice.

Non-destructive and rapid estimation of canopy variables is imperative for predicting crop growth and managing nitrogen (N) application. Hyperspectral remote sensing can be used for timely and accurate estimation of canopy physical and chemical properties; however, discrepancies associated with soil and water backgrounds complicate the estimation of crop N status using canopy spectral reflectance (CSR). This study established the quantitative relationships between dynamic canopy nitrogen (CN) status indicators, leaf dry weight (LDW), leaf N concentration (LNC), leaf N accumulation (LNA), and CSR-derived new hyperspectral vegetation indices (HVIs), and to access the plausibility of using these relationships to make in-season estimations of CN variables at the elongation (EL), booting (BT), and heading (HD) stages of rice crop growth. Two-year multi-N rate field experiments were conducted in 2015 and 2016 in Hubei Province, China, using the rice cultivar Japonica. The results showed that the sensitive spectral regions were negatively correlated with CN variables in the visible (400-720 nm and 560-710 nm) regions, and positively correlated (r > 0.50, r > 0.60) with red and NIR (720-900 nm) regions. These sensitive regions are used to formulate the new (SR777/759, SR768/750) HVIs to predict CN variables at the EL, BT, and HD stages. The newly developed stepwise multiple linear regression (SMLR) models could efficiently estimate the dynamic LDW at the BT stage and LNC and LNA at the HD stage. The SMLR models performed accurately and robustly when used with a validation data set. The projected results offer a suitable approach for rapid and accurate estimation of canopy N-indices for the precise management of N application during the rice growth period.

[Simulation on the restoration effect of soil moisture in alfalfa (Medicago sativa)-grain rotation system in semi-arid and drought-prone regions of Loess Plateau].

With the combination of field survey and EPIC modeling, this paper simulated the restoration effect of soil moisture in different alfalfa (Medicago sativa)-grain rotation systems in semi-arid and drought-prone regions of Loess Plateau. In perennial alfalfa field and in grain crop field after alfalfa, the correlation coefficients between the simulated and observed values of soil moisture content in 0-10 m layer were larger than 0.9 (P < 0.01), and their relative root mean square errors were between 0.05 and 0.16, with the relative errors less than 10%. The dynamic changes of the simulated soil moisture contents in different soil layers were consistent with those of the observed values. In the study regions, it was difficult for the restoration of soil moisture in the deep soil layers of alfalfa field. During the cultivation of alfalfa, the soil moisture content in the layers at 8-10 m depth should not be less than 5.7%. Considering the sustainable development of agricultural production, the appropriate cultivation duration of alfalfa should be 4-6 years and no more than 8 years. For the restoration of soil moisture after alfalfa cultivation in the study regions, the rotation system potato (Solanum tuberosum) --> potato --> spring wheat (Triticum aestivum) could be adopted, and alfalfa could be cultivated again after 32-33 years.