Precision Farming
R. Azadnia; A. Rajabipour; B. Jamshidi; M. Omid
Abstract
IntroductionApple is one of the most frequently consumed fruits in the world. It is a source of minerals, fiber, various biological compounds such as vitamin C, and phenolic compounds (natural antioxidants). The amount of nutrients plays a significant role in the growth, reproduction, and performance ...
Read More
IntroductionApple is one of the most frequently consumed fruits in the world. It is a source of minerals, fiber, various biological compounds such as vitamin C, and phenolic compounds (natural antioxidants). The amount of nutrients plays a significant role in the growth, reproduction, and performance of agricultural products and plants. Chemical inputs can be accurately managed by predicting these elements. Thus, timely and accurate monitoring and managing the status of crop nutrition is crucial for adjusting fertilization, increasing the yield, and improving the quality. This approach minimizes the application of chemical fertilizers and reduces the risk of environmental degradation. In crop plants, leaf samples are typically analyzed to diagnose nutrient deficiencies and imbalances, as well as to evaluate the effectiveness of the current nutrient management system. Therefore, the main aim of this study is to estimate the level of Nitrogen (N), Phosphorus (P), and Potassium (K) elements in the leaves of the apple tree using the non-destructive method of Visible/Near-infrared (Vis/NIR) spectroscopy at the wavelength range of 500 to 1000 nm coupled with chemometrics analysis.Materials and MethodsThis research investigated the potential of the Vis/NIR spectroscopy coupled with chemometrics analysis for predicting NPK nutrient levels of apple trees. In this study, 80 leaf samples of apple trees were randomly picked and transferred to the laboratory for spectral measurement. The Green-Wave spectrometer (StellarNet Inc, Florida, USA) was utilized to collect the spectral data. In the next step, the spectral data were transferred to the laptop using the Spectra Wiz software (StellarNet Inc, Florida, USA). For this purpose, spectroscopy of the leaf samples was done in interactance mode. Ten random points were selected on each leaf to capture reflectance spectra and the averaged spectrum was used to determine the reflectance (R). The data was then transformed into absorbance (log 1/R) for chemometrics analysis. Following the spectroscopy measurements, the NPK contents were measured using reference methods. Afterward, Partial Least Square (PLS) multivariate calibration models were developed based on the reference measurements and spectral information using different pre-processing techniques. To remove the unwanted effects, various pre-processing methods were utilized to obtain an accurate calibration model. To evaluate the proposed models, the Root Mean Square Error of calibration and prediction sets (RMSEC and RMSEP), as well as the correlation coefficient of calibration and prediction sets (rc and rp), and Residual Predictive Deviation (RPD) were calculated.Results and DiscussionThe statistical metrics were calculated for the evaluation of PLS models and the results indicated that the PLS models could efficiently predict the NPK contents with satisfactory accuracy. The model with the best performance for nitrogen prediction was based on the standard normal variate pre-processing method in combination with the second derivative (SNV+D2) and resulted in rc= 0.988, RMSEC=0.028%, rp=0.978, RMSEP=0.034%, and RPD of 7.47. The best model for P content prediction resulted in rc= 0.967, RMSEC=0.0051%, rp=0.958, RMSEP=0.0057%, and RPD of 5.96. Additionally, the PLS model based on MSC+D2 pre-processing method resulted in rc= 0.984, RMSEC=0.017%, rp=0.976, RMSEP=0.021%, and RPD of 7.10, indicating the high potential of PLSR model in predicting K content. Moreover, the weakest performing model was related to the estimation of P content without pre-processing with rc = 0.774, RMSEC = 0.013%, rp = 0.685, RMSEP = 0.018%, and RPD value of 1.87. Based on the obtained results, the proposed PLS models coupled with suitable pre-processing methods were able to predict the nutrient content with high precision.ConclusionField spectroscopy has recently gained popularity due to its portability, ease of use, and low cost. Consequently, the use of a portable system for estimating nutrient levels in the field can significantly save time and lower laboratory expenses. Therefore, due to the accuracy of the Vis/NIR spectroscopy technique and according to the obtained results, this method can be used to actualize a portable system based on Vis/NIR spectroscopy to estimate the nutrient elements needed by the apple trees in the orchards and to increase the productivity of the orchards.
Precision Farming
N. Bagheri; M. Safari; A. Sheikhi Garjan
Abstract
IntroductionAbout 30% of the annual losses of agricultural products are caused by pests, diseases, and weeds. Spraying is currently the most common method of their control. At present, various manual and tractor-mounted sprayers are used for spraying. Manual spraying has very low work efficiency and ...
Read More
IntroductionAbout 30% of the annual losses of agricultural products are caused by pests, diseases, and weeds. Spraying is currently the most common method of their control. At present, various manual and tractor-mounted sprayers are used for spraying. Manual spraying has very low work efficiency and is damaging as the spray might be applied irregularly and consumed by the labor or the product at poisonous levels. Tractor-mounted sprayers are more efficient than manual sprayers and require less labor. However, their use is associated with issues such as compacting the soil or crushing the product. In recent years, Unmanned Aerial Vehicle (UAV) sprayers have been used to spray farms and orchards. UAV spraying can increase the spraying efficiency by more than 60% and reduce the volume of spray used by 20-30%. Based on the capabilities of the UAV sprayer and the limitations of other current spraying methods, the purpose of this research is to evaluate the performance of the UAV sprayer in controlling Brevicoryne brassicae (L.) and compare the results with a turbo liner sprayer.Materials and MethodsIn the present research, the UAV sprayer is studied as a new method of spraying to fight Brevicoryne brassicae (L.). The results were technically and economically evaluated and compared with the control group and that of the turbo liner sprayer (the conventional method of spraying canola in Iran). The experiment was triplicated with a completely randomized design and three treatments of UAV sprayer, turbo liner sprayer, and control (no spraying). Field tests were conducted on the canola crop at the stemming stage where at least 20% of the plants were infected. The measured parameters included drift, spraying quality, field capacity, field efficiency, energy consumption, and spraying efficiency.Results and DiscussionBased on the results, the spray volume consumed by UAV and turbo liner sprayers was equal to 11.1 and 187.6 liters per hectare, respectively. The particle drift in spraying with UAV sprayer and turbo liner sprayer were 53.3% and 80%, respectively. Moreover, the quality coefficient of UAV and turbo liner sprayers were 1.15 and 1.21, respectively. Therefore, the farm efficiency of the UAV sprayer and turbo liner sprayer was equal to 51.4% and 32.3%, respectively. Based on the results of the analysis of variance, immediately after spraying, there was no statistically significant difference between the average density of pests of the three treatments. However, three, seven, and 14 days after spraying, there was a significant difference between the control treatment and the spraying treatments. The density of pests in the plots sprayed with UAV and turbo liner sprayers was lowered to less than 100 pests per stem, whereas in the control treatment, the density varied between 250-700 pests per stem. A comparison of the average efficiency of the UAV sprayer and turbo liner sprayer with the t-test showed that both sprayers had managed to control the population of pests and 14 days after the spraying, the efficiency of the UAV sprayer was higher than that of the turbo liner sprayer.Conclusion- The spray volume consumed by the turbo liner sprayer was 17 times the UAV sprayer.- The spray drift was about 34% more in spraying with the turbo liner sprayer than the UAV sprayer.- The field efficiency of the UAV sprayer was 59.1% more than the turbo liner sprayer.- The energy consumption per hectare of the turbo liner sprayer was 7 times the energy consumption of the UAV sprayer.- UAV sprayer’s efficiency reached 92.7 % 14 days after spraying.- UAV sprayer is recommended for controlling Brevicoryne brassicae (L.) due to its high efficiency, low drift, low spray volume and energy consumption, and superior spraying quality.- To improve the performance of the UAV sprayer for controlling Brevicoryne brassicae (L.), a flight height of 1-1.5 meters from the top of the crop, a flight speed of less than 7 m s-1, and a maximum spraying speed of 4 m s-1 are recommended. Additionally, it is possible to prevent the spread of the pest in the stemming stage by spraying the field in an earlier stage.
Precision Farming
M. Saadikhani; M. Maharlooei; M. A. Rostami; M. Edalat
Abstract
IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral ...
Read More
IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral images. One of the factors that reduces the accuracy of the classification map is the existence of uneven surfaces and high-altitude areas. The presence of high-altitude points makes it difficult for the sensors to obtain accurate reflection information from the surface of the phenomena. Radar imagery used with the digital elevation model (DEM) is effective for identifying and determining altitude phenomena. Image fusion is a technique that uses two sensors with completely different specifications and takes advantage of both of the sensors' capabilities. In this study, the feasibility of employing the fusion technique to improve the overall accuracy of classifying land coverage phenomena using time series NDVI images of Sentinel 2 satellite imagery and PALSAR radar imagery of ALOS satellite was investigated. Additionally, the results of predicted and measured areas of fields under cultivation of wheat, barley, and canola were studied.Materials and MethodsThirteen Sentinel-2 multispectral satellite images with 10-meter spatial resolution from the Bajgah region in Fars province, Iran from Nov 2018 to June 2019 were downloaded at the Level-1C processing level to classify the cultivated lands and other phenomena. Ground truth data were collected through several field visits using handheld GPS to pinpoint different phenomena in the region of study. The seven classes of distinguished land coverage and phenomena include (1) Wheat, (2) Barley, (3) Canola, (4) Tree, (5) Residential regions, (6) Soil, and (7) others. After the preprocessing operations such as radiometric and atmospheric corrections using predefined built-in algorithms recommended by other researchers in ENVI 5.3, and cropping the region of interest (ROI) from the original image, the Normalized Difference Vegetation Index (NDVI) was calculated for each image. The DEM was obtained from the PALSAR sensor radar image with the 12.5-meter spatial resolution of the ALOS satellite. After preprocessing and cropping the ROI, a binary mask of radar images was created using threshold values of altitudes between 1764 and 1799 meters above the sea level in ENVI 5.3. The NDVI time series was then composed of all 13 images and integrated with radar images using the pixel-level integration method. The purpose of this process was to remove the high-altitude points in the study area that would reduce the accuracy of the classification map. The image fusion process was also performed using ENVI 5.3. The support Vector Machine (SVM) classification method was employed to train the classifier for both fused and unfused images as suggested by other researchers.To evaluate the effectiveness of image fusion, Commission and Omission errors, and the Overall accuracy were calculated using a Confusion matrix. To study the accuracy of the estimated area under cultivation of main crops in the region versus the actual measured values of the area, regression equation and percentage of difference were calculated.Results and DiscussionVisual inspection of classified output maps shows the difference between the fused and unfused images in classifying similar classes such as buildings and structures versus regions covered with bare soil and lands under cultivation versus natural vegetation in high altitude points. Statistical metrics verified these visual evaluations. The SVM algorithm in fusion mode resulted in 98.06% accuracy and 0.97 kappa coefficient, 7.5% higher accuracy than the unfused images.As stated earlier, the similarities between the soil class (stones and rocks in the mountains) and manmade buildings and infrastructures increase omission error and misclassification in unfused image classification. The same misclassification occurred for the visually similar croplands and shallow vegetation at high altitude points. These results were consistence with previous literature that reported the same misclassification in analogous classes. The predicted area under cultivation of wheat and barley were overestimated by 3 and 1.5 percent, respectively. However, for canola, the area was underestimated by 3.5 percent.ConclusionThe main focus of this study was employing the image fusion technique and improving the classification accuracy of satellite imagery. Integration of PALSAR sensor data from ALOS radar satellite with multi-spectral imagery of Sentinel 2 satellite enhanced the classification accuracy of output maps by eliminating the high-altitude points and biases due to rocks and natural vegetation at hills and mountains. Statistical metrics such as the overall accuracy, Kappa coefficient, and commission and omission errors confirmed the visual findings of the fused vs. unfused classification maps.
Precision Farming
J. Nasrollahi Azar; R. Farrokhi Teimourlou; V. Rostampour
Abstract
IntroductionPrecision agriculture is a modern approach to farming that ensures the crops and soil receive exactly what they need for optimum health and productivity. Precision agriculture offers the potential to automate and simplify the collection and analysis of information. It allows management decisions ...
Read More
IntroductionPrecision agriculture is a modern approach to farming that ensures the crops and soil receive exactly what they need for optimum health and productivity. Precision agriculture offers the potential to automate and simplify the collection and analysis of information. It allows management decisions to be quickly made and implemented in small areas of larger fields. Measuring acoustic signals with a cone penetrometer is an advanced and inexpensive method that provides a lot of information about the soil within the shortest amount of time and with the lowest cost. The texture of the soil determines the percentage of the constituents of the mineral part of the soil such as sand, silt, and clay.In this study, an acoustic penetrometer is developed to provide an accurate method for determining the soil texture. This system uses a microphone to record the sound produced by the cone-soil contact and correlates this data with the soil texture.Materials and MethodsAn acoustic cone penetrometer (ACPT) was designed to determine if there is a relationship between the sound produced at the cone-soil contact and soil particle size. Three types of cones with angles of 30, 45, and 60 degrees, diameter of 20.27 mm, and rod length of 300 mm according to ASAE standard S313.3 FEB1999ED (R2013) were used to determine the relationship between sound and soil texture and to choose the best angle. A microphone (20-20,000 Hz) suitable for fast dynamic responses was used to record the audio signals produced from the soil. Audio signals were stored online through the oscilloscope section of Matlab software. To create the controlled vertical movement of the cones, a mechanical mechanism with electronic controllers was designed. This mechanism can be connected to the rails of the soilbin available in Urmia University, Iran, and is made of a 5 hp electric motor with a gearbox, an inverter for controlling the rotational speed of the electric motor, and a digital ruler for recording vertical movement. Soil samples were tested in 19-liter bins.Acoustic signals received from the microphone were processed in the time-frequency domain using wavelet transform. In this research, Daubechi function type 3 is used to analyze acoustic signals. It is not possible to use the processed acoustic signals directly for statistical analysis. Therefore, the relevant features should be extracted from them. From the 30 features of time domain signals, the most effective and main features include: SUM, Max, RMS, average, Var, kurtosis, and Moment4. They were ranked using the feature selection section of WEKA 3.9.2 software to avoid increasing the volume of calculations, increase processing speed, and reduce errors. The characteristic vector of the sub-signals of several different soil samples was analyzed to distinguish the soil type and constituents namely sand, silt, and clay.Results and DiscussionThe best type of cone was selected using WEKA software. The number of features in the d1 sub-signals was higher for the 45-degree cone, and it can be concluded that with this cone, the soil type can be better recognized.The average values of characteristics in clay, loam, and sand had an increasing trend, respectively, and were statistically significant with a probability of 1% and 5%.Acoustic signals for clay soil, which has a heavy texture and small particles, have minimum amplitude, and for loamy and sandy soils, they were observed as medium and maximum, respectively. This will cause the values of the selected features of clay soil to be low, and as a result, the average values, variance, and standard deviation are also low. They would be higher for loamy and sandy soil which have larger particles. It can be deduced that, as the size of the soil particles increases, the particles hitting the cone wall would become heavier and would affect the frequency and amplitude of the signal. This will result in the increase of signal amplitude values and, the sum, max, and mean values as well.ConclusionAmong the sub-signals, the maximum effect of soil texture type changes was related to d1 sub-signals for the 45̊ cone, and these signals had more potential to identify the soil texture type. Among the features, the sum, average, VAR, and RMS were significant at 1% probability levels. Therefore, these features have more potential to detect the type of soil texture in the mentioned sub-signal. Additionally, the effect of soil texture change on Moment and Kurtosis characteristics was significant at 5% probability levels.
Precision Farming
B. Besharati; A. Jafari; H. Mousazadeh; H. Navid
Abstract
IntroductionVarious methods have been performed to control weeds in the world and the use of herbicides is one of them, but public concerns about human health have changed interest in alternative methods. Thermal methods based on flame-weeder, hot air, steam, and hot water have the potential to control ...
Read More
IntroductionVarious methods have been performed to control weeds in the world and the use of herbicides is one of them, but public concerns about human health have changed interest in alternative methods. Thermal methods based on flame-weeder, hot air, steam, and hot water have the potential to control weeds, but due to the high cost are not economical. Electromagnetic waves transfer energy into weeds and finally destroy them. The effect of radiation on plant mutation, high consumption of energy, and human health are problems for this approach. Unlike other methods, electrical energy is an ideal and non-chemical method for weeds. This method applies high voltage to weeds, their roots, and soil so that electric currents pass through them, and the vaporization of the liquid content of weeds kills the weeds. To increase the severity of damage to weeds, the development of a feedback mechanism is required. The ultrasonic sensor measuring physical parameters like plant height is a simple method. Some complex sensing systems include optical sensors such as infrared, and machine vision that require high-speed processors and expensive equipment. In this project, as a simple method, the monitoring of the electrical current passing through weeds was used for developing the feedback mechanism and increasing electric damage to weeds.Materials and MethodsIn this study, the system consisted of a high-voltage device that generated a 15 kV AC voltage to kill weeds, as well as a feedback mechanism that included a sensor to measure the electric current on the input of the weed killer and identify the presence of weeds and their annihilation. All parts were installed on a robotic platform, and an application on a laptop was connected to it via an access point for navigation and data reception. The system was tested in a greenhouse lab with various weeds. Initially, a test was performed to investigate the effect of high voltage on the weeds and establish relationships between the electric currents passing through weeds and their presence (before and after annihilation). During the test, the system was guided along a path and applied high voltage to kill the weeds. The feedback mechanism was then calibrated based on the extracted data on electric current relations. This allowed the system to detect weeds and their annihilation, enabling it to move to the next target once a weed had been eliminated. After calibration, a comparative test was conducted to evaluate the weed-killing efficiency of the two methods (with and without the feedback mechanism), and the results were analyzed using a t-test with p ≤ 0.01.Results and DiscussionThe observations indicated that the input electric current on the weed killer was dependent on the electric current passing through weeds. When the high-voltage electrode touched a weed, the electric current passed through it increased, and simultaneously, the high electrical energy destroyed the weed. After the removal of the weed, the electric current rapidly decreased. The average energy consumption per weed plant was estimated to be 250 joules, which can be compared with other methods. The final test comparing the use and non-use of the feedback mechanism revealed significant differences (P < 0.01) between the results obtained with and without the mechanism, demonstrating that the feedback mechanism increased the efficiency of weed annihilation. The sensing system used in the developed feedback mechanism is a simple method that is affected by the electrical resistivity of weeds. As such, it did not mistakenly detect other objects as weeds, unlike an ultrasonic mechanism. Based on these results, monitoring the electrical current passing through weeds proved to be a suitable method for developing a feedback mechanism for the weed killer to identify the presence of weeds and their annihilation.ConclusionThe use of high voltage as a non-chemical and alternative method for weed control has shown promising results. The study revealed that measuring the electric current applied to the weed killer was an effective and straightforward approach to developing a feedback mechanism. This mechanism aids in identifying the presence of weeds and ensuring their elimination by intensifying the damage inflicted on them through the application of high electrical energy. To further enhance the efficiency and speed of weed control, future research should consider integrating an automatic guidance mechanism with the weed killer.
Precision Farming
H. Mohamadi-Monavar; S. Zibazadeh
Abstract
IntroductionRemote sensing methods for mapping farms and crops have been widely used in the last three decades. This method is applied to identify irrigated areas around the world (Alipour et al., 2014), although most of these studies are in areas with semi-arid climates and low rainfall or lack of rainfall ...
Read More
IntroductionRemote sensing methods for mapping farms and crops have been widely used in the last three decades. This method is applied to identify irrigated areas around the world (Alipour et al., 2014), although most of these studies are in areas with semi-arid climates and low rainfall or lack of rainfall which has a significant effect on the spectral characteristics of plants. In this study, Landsat 8 and MODIS satellite images were used to identify and separate two irrigated and rain-fed wheat farms in Hamadan province. Two algorithms of support vector machine (SVM) and minimum distance (MD) were used simultaneously to classify irrigated and rain-fed farms. In the next step, the area under cultivation of rain-fed and irrigated wheat was predicted in the whole cultivated area of Hamadan province. Finally, the cultivation area of rain-fed and irrigated crops was calculated in the province using Sentinel 3 satellite images based on the random forest algorithm in 2016.Materials and MethodsThe study area is Hamedan province, which is located between 59◦ 33′ and 49◦ 35′ north latitude and also from 34◦ 47′ to 34◦ 49′ east longitude of the Greenwich meridian. A 50-hectare rain-fed wheat farm in Amzajerd was used as a sample to extract the properties of rain-fed wheat. Also, irrigated indices were extracted from a 100-hectare irrigated wheat farm located in Kaboudrahang. Satellite images were applied to separate irrigated and rain-fed wheat in Hamadan province. NDVI, EVI and NDWI indices were extracted from 16-day images of Landsat, MODIS, and Sentinel 3 sensors in the five-year period (2015-2019). Google Earth Engine (GEE) system was the environment for performing image processing calculations and extracting indices and maps.Results and DiscussionThe NDVI and EVI of irrigated and rain-fed wheat farms were calculated in 2015-2019. A small peak was observed in the rain-fed and irrigated NDVI trend in November due to the early germination of wheat leaves in winter, and the larger peak in May and June showed the maximum greenness of irrigated and rain-fed wheat, respectively. The ascending or descending trend of NDVI / EVI had no constant slope. This can be due to changes in meteorological parameters, which sometimes cause a sudden increase or decrease in the values of these indices. Despite the non-linearity of the NDVI / EVI trend over time, the maximum greenness was recorded just a month before the wheat harvest, which was seen in the third decade of May to the first decade of June. One of the cases is the sharp drop of NDVI / EVI after its final peak, which was definitely due to yellowing wheat and harvesting. Since the distinction between rain-fed and irrigated crops was difficult only based on NDVI, NDWI was also used to determine the water content of wheat so that irrigated wheat could be identified. However, the difference between rain-fed and irrigated wheat in terms of NDWI spectral density was insignificant; the maximum and minimum occurrence times of NDWI and NDVI of rain-fed and irrigated wheat were chosen for their separation. In order to map the cultivation area, in addition to the MODIS sensor, Sentinel 3 was used due to its ability to detect chlorophyll accurately. Due to the fact that the imaging of the Sentinel 3 satellite started since 2016, the map of rain-fed and irrigated cultivation as well as the cultivation area and their separation was done based on the random forest algorithm in 2016.ConclusionThe results of this study showed that the appropriate method for distinguishing between rain-fed and irrigated wheat is the simultaneous use of several indices. Also, the greatest difference is in the maximum greenness, which happened almost one month before harvest. MD and SVM classification algorithms could distinguish irrigated and rain-fed wheat from other crops with 90% and 80% accuracy, respectively. Distinguished maps of irrigated and rain-fed crops based on the random forest algorithm were obtained using Sentinel 3 satellite imagery which can show the fertility of agricultural lands in the province.
Precision Farming
F. Nadernejad; D. M. Imani; M. R. Rasouli
Abstract
IntroductionSugarcane is a strategic agricultural product and increasing productivity and self-sufficiency in its production is of special importance. The most important product of sugarcane is sugar. Various factors like climatic and management conditions affect the yield of sugarcane and recoverable ...
Read More
IntroductionSugarcane is a strategic agricultural product and increasing productivity and self-sufficiency in its production is of special importance. The most important product of sugarcane is sugar. Various factors like climatic and management conditions affect the yield of sugarcane and recoverable sugar. Crop yield forecasting is one of the most important topics in precision agriculture, which is used to estimate yield, match product supply with demand and manage product to increase productivity. The purpose of this study is to predict and model the factors affecting sugar extracted from sugarcane (recoverable sugar) in the farms of Amir-Kabir sugarcane agro-industry Company of Khuzestan province using machine learning methods.Materials and MethodsTo conduct this study, data from the agro-industrial company Amir-Kabir in the province of Khuzestan from 2010 to 2017 were used. This data has 3223 records which include four sets of data: climate, soil, crop and farm management. This data includes continuous and discrete variables. Discrete variables include production management, soil type, farm, variety, age (cane class), the month of harvest and times irrigation. Continuous variables include area, chemical fertilizer consumption, water consumption per hectare, total water consumption, drain, crop season duration, yield (cane yield) soil EC, purity, time interval drying off to crop harvest, precipitation, min and max temperature, min and max relative humidity, wind speed and evaporation. The recoverable sugar variable is considered as the target variable and is divided into two classes, values greater than or equal to 9 are in the optimal class and less than 9 are in the undesirable class. The other variables are considered as predictor variables. For modeling using the Holdout method the data were randomly divided into two independent sets, a training set and a test set. 70% of the data which includes 2256 records were used for training and 30% of the data which includes 967 records were used for testing. The modeling of this study was performed with the Python programming language version 3.8.6 in the Jupyter notebook environment. Random Forest, Adaboost, XGBoost and SVM (support vector machine) algorithms were used for modeling.Results and DiscussionTo evaluate the models, metrics of accuracy, precision, recall, f1 score and k-fold cross validation were used. The XGBoost model with 94.8% accuracy on the training set and the Adaboost model with 92.4% accuracy on the test set, are the best models. Based on precision and recall metrics Adaboost model with 87% precision and SVM model with 87% recall have better performance than the other models. Based on Repeated 10-fold stratified cross validation using two repeats the SVM model with 92.3% accuracy is the best model. The variables of purity, time interval drying off to crop harvest and crop season duration are the most important variables in predicting the recoverable sugar.ConclusionIn this study a new approach based on machine learning methods for predicting recoverable sugar from sugarcane was presented. The most important innovation of this study is the simultaneous consideration of management and climatic factors, along with other factors such as soil and crop characteristics for modeling and classification the recoverable sugar percentage from sugarcane. The results show that the performance of all models is acceptable and machine learning methods and ensemble learning algorithms can be used to predict crop yield. The results of this study and the analysis of the rules obtained from the set of decision trees made in the random forest model can be used for managers of different agro-industries in determining appropriate strategies and preparing the conditions to achieve optimal production.For future research as well as policy making and decision making Amir-Kabir sugarcane agro-industry Company the following suggestions are offered: more samples can be used to obtain more reliable results. Also can be used Deep learning methods, time series analysis and image processing. Use of IOT equipment to collect and real-time processing data on Amir-Kabir sugarcane agro-industry farms.
Precision Farming
M. Hashemi Jozani; H. Bagherpour; J. Hamzei
Abstract
Fractional vegetation cover (FVC) and normalized difference vegetation index (NDVI) are the most important indicators of greenness and have a strong correlation with green biomass. The objective of this study was to evaluate a hand-held GreesnSeeker (GS) active remote sensing instrument to estimate NDVI ...
Read More
Fractional vegetation cover (FVC) and normalized difference vegetation index (NDVI) are the most important indicators of greenness and have a strong correlation with green biomass. The objective of this study was to evaluate a hand-held GreesnSeeker (GS) active remote sensing instrument to estimate NDVI and FVC in the spinach plant. In this study, the color indices of the G-B index and Excess Green (ExG) were used as color vegetation indices to discriminate leaves from soil background. During 28 to 44 days after emergence (DAG), the results showed good correlations between chlorophyll yield and NDVI (R = 0.61 to 0.91), and the correlation between NDVI of GS and biomass was significant. In addition, in this growth stage, the results showed a good coefficient of correlation between NDVI of GS and FVC (R = 0.67 to 0.82). In assessing the nitrogen rate on the NDVI of GS, the results showed significant differences only at the short period of growth stage (28 to 36 DAG). The results revealed that GreenSeeker performed well for estimation both chlorophyll and biomass yield of spinach crop and it could be used as a suitable instrument for estimation of leaf area index in the middle of the plant growth period.
