Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964647
S. Gianessi, M. Polo, L. Stevanato, M. Lunardon, G. Baroni
Soil moisture is a key variable for supporting agriculture and forest management. This variable, however, shows strong variability in space and time and its correct quantification is still difficult in many practical applications. In the present study we compare two innovative non-invasive sensors developed for the estimation of soil moisture over large area. The first one is a new sensor based on cosmic-ray neutron sensing approach. The second one is a new gamma-ray spectrometer specifically designed for this type of application. Data have been collected at a large, cropped field at Ceregnano, Italy in 2021. The results show that both sensors well capture the local hydrological conditions, and they can be considered reliable methods for soil moisture estimations. In both sensors, however, the signal shows to also be sensitive even if to a different degree to water in the biomass, highlighting the need of corrections when fast plant growth is expected.
{"title":"Comparison of cosmic-ray neutron sensing and gamma-ray spectrometry for non-invasive soil moisture estimation over a large cropped field","authors":"S. Gianessi, M. Polo, L. Stevanato, M. Lunardon, G. Baroni","doi":"10.1109/MetroAgriFor55389.2022.9964647","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964647","url":null,"abstract":"Soil moisture is a key variable for supporting agriculture and forest management. This variable, however, shows strong variability in space and time and its correct quantification is still difficult in many practical applications. In the present study we compare two innovative non-invasive sensors developed for the estimation of soil moisture over large area. The first one is a new sensor based on cosmic-ray neutron sensing approach. The second one is a new gamma-ray spectrometer specifically designed for this type of application. Data have been collected at a large, cropped field at Ceregnano, Italy in 2021. The results show that both sensors well capture the local hydrological conditions, and they can be considered reliable methods for soil moisture estimations. In both sensors, however, the signal shows to also be sensitive even if to a different degree to water in the biomass, highlighting the need of corrections when fast plant growth is expected.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133449780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964641
Alberto Zancanaro, Giulia Cisotto, Dagmawi Delelegn Tegegn, Sara L. Manzoni, Ivan Reguzzoni, E. Lotti, I. Zoppis
The digitalization of the agrifood market is increasingly demanding for new technologies to support its transition towards smart agriculture, a sustainable food industry, and efficient management of greenhouses and crop breeding. In this work, we aim to exploit two emerging and promising technologies with application to the early detection of stressful conditions in plants. Two high-resolution near-infrared spectrometers, spanning the range from 1350 nm to 2150 nm, were used to acquire the reflectance spectra from a pothos (Epipremnum aureum) in two different hydration conditions, i.e., normal and anomalous. Then, we trained a machine learning model, i.e., a $beta$ -variational autoencoder ($beta$ - VAE), to identify the anomalies in the hydration of the plant over three months of acquisition. We are able to show the feasibility of our proposed combination of near-infrared spectrometry and the $beta$ - VAE to accurately identify anomalies, i.e., to detect stressful conditions in plants. This contributes to the recent and promising advancements in smart agriculture, by exploiting a new generation of high-resolution, portable, and non-destructive near-infrared sensing technology and powerful machine learning data analytics.
{"title":"Variational Autoencoder for Early Stress Detection in Smart Agriculture: A Pilot Study","authors":"Alberto Zancanaro, Giulia Cisotto, Dagmawi Delelegn Tegegn, Sara L. Manzoni, Ivan Reguzzoni, E. Lotti, I. Zoppis","doi":"10.1109/MetroAgriFor55389.2022.9964641","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964641","url":null,"abstract":"The digitalization of the agrifood market is increasingly demanding for new technologies to support its transition towards smart agriculture, a sustainable food industry, and efficient management of greenhouses and crop breeding. In this work, we aim to exploit two emerging and promising technologies with application to the early detection of stressful conditions in plants. Two high-resolution near-infrared spectrometers, spanning the range from 1350 nm to 2150 nm, were used to acquire the reflectance spectra from a pothos (Epipremnum aureum) in two different hydration conditions, i.e., normal and anomalous. Then, we trained a machine learning model, i.e., a $beta$ -variational autoencoder ($beta$ - VAE), to identify the anomalies in the hydration of the plant over three months of acquisition. We are able to show the feasibility of our proposed combination of near-infrared spectrometry and the $beta$ - VAE to accurately identify anomalies, i.e., to detect stressful conditions in plants. This contributes to the recent and promising advancements in smart agriculture, by exploiting a new generation of high-resolution, portable, and non-destructive near-infrared sensing technology and powerful machine learning data analytics.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116533256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964826
V. Bagarello, V. Ferro, V. Pampalone
The Universal Soil Loss Equation (USLE) is still widely used to predict soil loss by water erosion and to establish soil conservation measures. In this model, the soil erodibility factor $K$ accounts for the susceptibility of the soil to be eroded due to the detachment and transport processes operated by the erosive agents. According to the USLE scheme, the $K$ factor should be measured on unit plots, i.e., bare plots of given length (22 m) and steepness (9%) tilled along the maximum slope direction, but there is little evidence that there ever existed an actual unit plot between the plots used to develop the USLE. Given the difficulty in collecting sufficient data to adequately measure $K$., the nomograph method was early developed to allow estimation of $K$ based on standard soil properties. First, in this investigation the soil erodibility factor was experimentally determined for the clay soil of the Sparacia (Sicily) experimental station, based on the available measurements collected in two unit plots. Although a limited database was available for this analysis, a very low value (0.0038 t ha h ha−1 MJ−1 mm−1) was determined, which was an order of magnitude lower than the nomograph value. Then, the values of the plot steepness factor $S$ were determined using soil loss measurements collected on plots varying in steepness from 9 to 26% and resulted higher than the estimated values by a well-known literature expression. Finally, the plot length factor $L$ resulted independent of the plot length and equal to one. The former result was explained by the different flow transport capacity in the unit plot and plot with increased steepness, while the result of a constant length factor was supported by other experimental investigations.
通用土壤流失方程(USLE)仍被广泛用于预测水土流失和制定水土保持措施。在该模型中，土壤可蚀性因子K反映了土壤在侵蚀剂作用下的分离和运移过程对侵蚀的敏感性。根据USLE方案，$K$因子应在单元地块上测量，即沿最大坡度方向耕作的给定长度(22 m)和坡度(9%)的裸地块，但几乎没有证据表明用于开发USLE的地块之间存在实际的单元地块。鉴于难以收集足够的数据来充分衡量$K$。在美国，nomograph方法很早就被开发出来，允许基于标准土壤性质来估计$K$。首先，在本研究中，基于在两个单元样地收集的可用测量数据，实验确定了Sparacia (Sicily)实验站粘土的土壤可蚀性因子。虽然可用于该分析的数据库有限，但确定了一个非常低的值(0.0038 tha h ha−1 MJ−1 mm−1)，比nomograph值低一个数量级。然后，利用在坡度为9% ~ 26%的样地上收集的土壤流失量来确定样地陡峭系数S$的值，其结果高于一个著名的文献表达式的估计值。最后，小区长度因子$L$的结果与小区长度无关，等于1。前者的结果可以用单元地块和陡度增加地块的输流量不同来解释，而恒定长度因子的结果也得到了其他实验研究的支持。
{"title":"Measuring the USLE soil erodibility factor in the unit plots of Sparacia (southern Italy) experimental area","authors":"V. Bagarello, V. Ferro, V. Pampalone","doi":"10.1109/MetroAgriFor55389.2022.9964826","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964826","url":null,"abstract":"The Universal Soil Loss Equation (USLE) is still widely used to predict soil loss by water erosion and to establish soil conservation measures. In this model, the soil erodibility factor $K$ accounts for the susceptibility of the soil to be eroded due to the detachment and transport processes operated by the erosive agents. According to the USLE scheme, the $K$ factor should be measured on unit plots, i.e., bare plots of given length (22 m) and steepness (9%) tilled along the maximum slope direction, but there is little evidence that there ever existed an actual unit plot between the plots used to develop the USLE. Given the difficulty in collecting sufficient data to adequately measure $K$., the nomograph method was early developed to allow estimation of $K$ based on standard soil properties. First, in this investigation the soil erodibility factor was experimentally determined for the clay soil of the Sparacia (Sicily) experimental station, based on the available measurements collected in two unit plots. Although a limited database was available for this analysis, a very low value (0.0038 t ha h ha−1 MJ−1 mm−1) was determined, which was an order of magnitude lower than the nomograph value. Then, the values of the plot steepness factor $S$ were determined using soil loss measurements collected on plots varying in steepness from 9 to 26% and resulted higher than the estimated values by a well-known literature expression. Finally, the plot length factor $L$ resulted independent of the plot length and equal to one. The former result was explained by the different flow transport capacity in the unit plot and plot with increased steepness, while the result of a constant length factor was supported by other experimental investigations.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122384090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964955
A. Altana, Lorenzo Becce, E. Avancini, P. Lugli, L. Petti, F. Mazzetto
The investigation of the performance of agricultural sprayer through drift and deposition sampling directly on field is of extreme importance, especially in view of ensuring an effective and optimal administration of plant protection products (PPP), necessary to limit waste of products and damages to the ecosystems. This is however a time and resource-intensive activity, typically resulting in highly variable results due to the unpredictable and uncontrollable atmospheric and operating conditions under which sprayers usually operate. To minimize the measurement uncertainties while also simpli-fying the procedures and reducing costs, in this work we propose a deposition assessment protocol based on the spraying of two distinct tracer solutions, leveraging two well-known phenomena: one based on optical absorbance, and the other on electrical conductivity. Although the selected tracers, namely uranine and potassium chloride, are already extensively used in other applications for their non-toxicity to both bystanders and environment, very little is published about their use in spray drift applications; the results obtained on the test bench promise to reduce the experiment costs, simplify the measurement, increase the reproducibility and facilitate the test automation. A test bench for nozzles has been employed to deposit the solutions on a matrix of Petri dishes; the original weight of deposited material in each sample is used, after complete drying and redissolution in fixed amounts of DI water, to verify the conductivity-concentration and absorbance-concentration laws. The two analyses show promising correlations, justifying an extended test campaign through further experiments, more representative of the actual spraying systems.
{"title":"Cost-effective tracing techniques for the rapid characterization of spray deposition and drift through electrical conductivity and fluorescence","authors":"A. Altana, Lorenzo Becce, E. Avancini, P. Lugli, L. Petti, F. Mazzetto","doi":"10.1109/MetroAgriFor55389.2022.9964955","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964955","url":null,"abstract":"The investigation of the performance of agricultural sprayer through drift and deposition sampling directly on field is of extreme importance, especially in view of ensuring an effective and optimal administration of plant protection products (PPP), necessary to limit waste of products and damages to the ecosystems. This is however a time and resource-intensive activity, typically resulting in highly variable results due to the unpredictable and uncontrollable atmospheric and operating conditions under which sprayers usually operate. To minimize the measurement uncertainties while also simpli-fying the procedures and reducing costs, in this work we propose a deposition assessment protocol based on the spraying of two distinct tracer solutions, leveraging two well-known phenomena: one based on optical absorbance, and the other on electrical conductivity. Although the selected tracers, namely uranine and potassium chloride, are already extensively used in other applications for their non-toxicity to both bystanders and environment, very little is published about their use in spray drift applications; the results obtained on the test bench promise to reduce the experiment costs, simplify the measurement, increase the reproducibility and facilitate the test automation. A test bench for nozzles has been employed to deposit the solutions on a matrix of Petri dishes; the original weight of deposited material in each sample is used, after complete drying and redissolution in fixed amounts of DI water, to verify the conductivity-concentration and absorbance-concentration laws. The two analyses show promising correlations, justifying an extended test campaign through further experiments, more representative of the actual spraying systems.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129221543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964672
M. Greco, E. Giovenale, F. Leccese, A. Doria
THz radiation is non-ionizing and non-invasive. Exploiting these features, THz technologies could be used to perform inspections on food quality control. The objective of this study is to discriminate healthy and rotten hazelnuts by using a 97 GHz imaging system.
{"title":"A Discrimination of Healthy and Rotten Hazelnuts Using a THz Imaging Scanner","authors":"M. Greco, E. Giovenale, F. Leccese, A. Doria","doi":"10.1109/MetroAgriFor55389.2022.9964672","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964672","url":null,"abstract":"THz radiation is non-ionizing and non-invasive. Exploiting these features, THz technologies could be used to perform inspections on food quality control. The objective of this study is to discriminate healthy and rotten hazelnuts by using a 97 GHz imaging system.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129328262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964832
Alessandra Vinci, Chiara Traini, D. Farinelli, Raffaella Brigante
Assessing the canopy characteristics of the trees is essential for optimizing agronomic management. In fact, it has been shown that there is a strong relationship between the geometric characteristics (i.e. size and volume) of the tree and quantity of water and fertilizer used for crop management. Normally, tree measurements are carried out using manual method, that is time consuming so seems to be more feasible on few trees. For the first time, this study tested the UAV technology on intensive and high-density hazelnut orchards. The aim was to propose a new automated method for the hazelnut canopy characterization, using a DJI Phantom 4 Multispectral UAV. The results showed a good performance of the method proposed for evaluating the width and the actual volume of the canopy. A criticism was revealed for the height of the canopy probably due to the UAV survey. Anyway, the measurements conducted on the point cloud resulted less time-consuming per each tree and more punctual than manual ones, so less exposed to errors.
{"title":"Assessment of the geometrical characteristics of hazelnut intensive orchard by an Unmanned Aerial Vehicle (UAV)","authors":"Alessandra Vinci, Chiara Traini, D. Farinelli, Raffaella Brigante","doi":"10.1109/MetroAgriFor55389.2022.9964832","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964832","url":null,"abstract":"Assessing the canopy characteristics of the trees is essential for optimizing agronomic management. In fact, it has been shown that there is a strong relationship between the geometric characteristics (i.e. size and volume) of the tree and quantity of water and fertilizer used for crop management. Normally, tree measurements are carried out using manual method, that is time consuming so seems to be more feasible on few trees. For the first time, this study tested the UAV technology on intensive and high-density hazelnut orchards. The aim was to propose a new automated method for the hazelnut canopy characterization, using a DJI Phantom 4 Multispectral UAV. The results showed a good performance of the method proposed for evaluating the width and the actual volume of the canopy. A criticism was revealed for the height of the canopy probably due to the UAV survey. Anyway, the measurements conducted on the point cloud resulted less time-consuming per each tree and more punctual than manual ones, so less exposed to errors.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128581689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9965011
Mattia Barezzi, Federico Cum, U. Garlando, Maurizio Martina, D. Demarchi
Smart agriculture offers an environmental-friendly path with respect to unsustainable farming that depletes the nutrients in the soil leading to a persistent degradation of ecosystems caused by population growth. Artificial Intelligence (AI) can help mitigate this issue by predicting plant health status to reduce the use of chemicals and optimize water usage. This paper proposes a custom framework to train neural networks and a comparison among different models to point out the impact and the importance of the stem electrical impedance in addition to environmental parameters for plant monitoring applications. In particular, the paper demonstrates how stem electrical impedance improves the accuracy of the proposed neural network application for plant status classification. The data set is composed of electrical impedance spectra and environmental data acquired on four tobacco plants for a two-month-long experiment. In this paper, we describe the acquisition system architecture, the feature composition of the data set, a general overview of the developed framework, and the training of the neural networks showing the different results considering both the stem impedance and the environmental parameters.
{"title":"On the impact of the stem electrical impedance in neural network algorithms for plant monitoring applications","authors":"Mattia Barezzi, Federico Cum, U. Garlando, Maurizio Martina, D. Demarchi","doi":"10.1109/MetroAgriFor55389.2022.9965011","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9965011","url":null,"abstract":"Smart agriculture offers an environmental-friendly path with respect to unsustainable farming that depletes the nutrients in the soil leading to a persistent degradation of ecosystems caused by population growth. Artificial Intelligence (AI) can help mitigate this issue by predicting plant health status to reduce the use of chemicals and optimize water usage. This paper proposes a custom framework to train neural networks and a comparison among different models to point out the impact and the importance of the stem electrical impedance in addition to environmental parameters for plant monitoring applications. In particular, the paper demonstrates how stem electrical impedance improves the accuracy of the proposed neural network application for plant status classification. The data set is composed of electrical impedance spectra and environmental data acquired on four tobacco plants for a two-month-long experiment. In this paper, we describe the acquisition system architecture, the feature composition of the data set, a general overview of the developed framework, and the training of the neural networks showing the different results considering both the stem impedance and the environmental parameters.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121198655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964799
L. Coviello, Francesco Maria Martini, L. Cesaretti, S. Pesaresi, F. Solfanelli, A. Mancini
The monitoring of cropland areas and in particular the capability to evaluate the performance of a field over space and time is becoming a crucial activity to schedule agronomic operations (e.g., fertilization) properly. In particular, the use of remotely sensed data opened new ways for this kind of analysis. In this work, we present a methodology based on Functional Data Analysis that starting from remotely sensed time-series data gen-erates cluster maps of a cropland area. Starting from vegetation index time-series data, Functional Principal Component Analysis (FPCA) was applied to derive FPCA scores and components. FPCA scores are then clusterized to obtain maps that embed the dynamics of crops over space and time. The derived maps can be used to optimize agronomic tasks such as fertilization also acting as base layers to create management zones and then prescription maps.
对耕地面积的监测，特别是在空间和时间上评价一块田地的表现的能力，正成为适当安排农艺作业(例如施肥)的一项关键活动。特别是，遥感数据的使用为这类分析开辟了新的途径。在这项工作中，我们提出了一种基于功能数据分析的方法，该方法从遥感时间序列数据开始生成农田区域的集群图。从植被指数时间序列数据出发，应用功能主成分分析(Functional Principal Component Analysis, FPCA)得到FPCA分数和成分。然后对FPCA分数进行聚类，以获得嵌入作物在空间和时间上的动态的地图。衍生的地图可以用来优化农艺任务，如施肥，也可以作为基础层来创建管理区域，然后是处方地图。
{"title":"Clustering of Remotely Sensed Time Series using Functional Principal Component Analysis to Monitor Crops","authors":"L. Coviello, Francesco Maria Martini, L. Cesaretti, S. Pesaresi, F. Solfanelli, A. Mancini","doi":"10.1109/MetroAgriFor55389.2022.9964799","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964799","url":null,"abstract":"The monitoring of cropland areas and in particular the capability to evaluate the performance of a field over space and time is becoming a crucial activity to schedule agronomic operations (e.g., fertilization) properly. In particular, the use of remotely sensed data opened new ways for this kind of analysis. In this work, we present a methodology based on Functional Data Analysis that starting from remotely sensed time-series data gen-erates cluster maps of a cropland area. Starting from vegetation index time-series data, Functional Principal Component Analysis (FPCA) was applied to derive FPCA scores and components. FPCA scores are then clusterized to obtain maps that embed the dynamics of crops over space and time. The derived maps can be used to optimize agronomic tasks such as fertilization also acting as base layers to create management zones and then prescription maps.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121050395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9964572
Alberto Udali, B. Talbot, S. Puliti, J. Crous, E. Lingua, S. Grigolato
The use of UAV based images in forestry allows for the coverage of large areas with a high level of detail. The combination of this information with machine learning (ML) techniques provides significant data for management and forest operations. This study focuses on evaluating the potential of UAVs based images and the use of ML algorithms to assess the distribution and classification of forest residues over clear felled areas. A random forest model was built using RGB bands, textural variables, and information from the surface model to classify elements in a clear felled site. The classification resulted in an overall accuracy of 91% with high values for coarse woody debris (CWD) and ground detection. We concluded that the method shows a significant and solid improvement for the classification of forest residues in clear felled sites.
{"title":"Assessing the potential for forest residue classification and distribution over clear felled areas using UAVs and Machine Learning: a preliminary case study in South Africa","authors":"Alberto Udali, B. Talbot, S. Puliti, J. Crous, E. Lingua, S. Grigolato","doi":"10.1109/MetroAgriFor55389.2022.9964572","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9964572","url":null,"abstract":"The use of UAV based images in forestry allows for the coverage of large areas with a high level of detail. The combination of this information with machine learning (ML) techniques provides significant data for management and forest operations. This study focuses on evaluating the potential of UAVs based images and the use of ML algorithms to assess the distribution and classification of forest residues over clear felled areas. A random forest model was built using RGB bands, textural variables, and information from the surface model to classify elements in a clear felled site. The classification resulted in an overall accuracy of 91% with high values for coarse woody debris (CWD) and ground detection. We concluded that the method shows a significant and solid improvement for the classification of forest residues in clear felled sites.","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126189015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroAgriFor55389.2022.9965078
A. Andreoli, Felix Pitscheider, Alessio Rozzoni, E. Tomelleri, F. Comiti
The current study was carried out in a wind damaged forest area and it aims to estimate the effects of management strategies after storm events on runoff and sediment yield. In order to achieve the goal, four experimental plots have been established on an area hit by two windthrows in 2003 and 2018 (Vaia storm). Each plot bound an area of 27 m2 (4.5 m x 6 m) and is located on a 40% slope facing East, previously covered with subalpine spruce forest at about 1650 m asl. The considered forest treatments were (1) salvage logging and natural regeneration, (2) no intervention, and (3) salvage logging and artificial regeneration. We measured runoff and sediments yield from September 2020 to September 2022. Water and sediments mobilized in the experimental plots are convoyed in a 1 m3 tank where the content is weighted by a load cell, and a pressure transducer records the water level. An in-situ radar rain gauge measures cumulative precipitation and intensity. Moreover, sediments samples were collected twice a year, dried and sieved to obtain the percentage of organic material and the texture of the eroded soil. The first results show a contrasting behaviour in terms of runoff/sediment yield between the four plots upon the occurrence of an intense precipitation event. The differences could be explained by the time passed after the windthrow, and the different forest treatments applied. These and future outcomes will be of paramount importance for adapting management strategies to an increasing frequency of subsequential extreme events (windthrow and precipitation).
{"title":"Effects of different forest recovery management on runoff and soil erosion in an area affected by Vaia storm","authors":"A. Andreoli, Felix Pitscheider, Alessio Rozzoni, E. Tomelleri, F. Comiti","doi":"10.1109/MetroAgriFor55389.2022.9965078","DOIUrl":"https://doi.org/10.1109/MetroAgriFor55389.2022.9965078","url":null,"abstract":"The current study was carried out in a wind damaged forest area and it aims to estimate the effects of management strategies after storm events on runoff and sediment yield. In order to achieve the goal, four experimental plots have been established on an area hit by two windthrows in 2003 and 2018 (Vaia storm). Each plot bound an area of 27 m2 (4.5 m x 6 m) and is located on a 40% slope facing East, previously covered with subalpine spruce forest at about 1650 m asl. The considered forest treatments were (1) salvage logging and natural regeneration, (2) no intervention, and (3) salvage logging and artificial regeneration. We measured runoff and sediments yield from September 2020 to September 2022. Water and sediments mobilized in the experimental plots are convoyed in a 1 m3 tank where the content is weighted by a load cell, and a pressure transducer records the water level. An in-situ radar rain gauge measures cumulative precipitation and intensity. Moreover, sediments samples were collected twice a year, dried and sieved to obtain the percentage of organic material and the texture of the eroded soil. The first results show a contrasting behaviour in terms of runoff/sediment yield between the four plots upon the occurrence of an intense precipitation event. The differences could be explained by the time passed after the windthrow, and the different forest treatments applied. These and future outcomes will be of paramount importance for adapting management strategies to an increasing frequency of subsequential extreme events (windthrow and precipitation).","PeriodicalId":374452,"journal":{"name":"2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132132209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：