A5061166761- Remote Sensing in Agriculture
- Leaf Properties and Growth Measurement
- Remote Sensing and LiDAR Applications
- Climate change impacts on agriculture
- Smart Agriculture and AI
- Irrigation Practices and Water Management
- Spectroscopy and Chemometric Analyses
- Soil and Land Suitability Analysis
- Crop Yield and Soil Fertility
- Soybean genetics and cultivation
- Soil Moisture and Remote Sensing
- Water Quality Monitoring Technologies
- Geography and Environmental Studies
- Agricultural and Food Sciences
- Land Use and Ecosystem Services
- Soil Management and Crop Yield
- Advanced Image Fusion Techniques
- Soil and Unsaturated Flow
- Plant Water Relations and Carbon Dynamics
- Greenhouse Technology and Climate Control
- Environmental and biological studies
- Remote Sensing and Land Use
- Conservation, Biodiversity, and Resource Management
- Precipitation Measurement and Analysis
- Soil Geostatistics and Mapping
Commonwealth Scientific and Industrial Research Organisation
2020-2025
Health Sciences and Nutrition
2022
Universidade Estadual do Oeste do Paraná
2016-2021
Agriculture and Food
2020-2021
University of Florida
2018-2019
Rogers (United States)
2019
Universidade Estadual do Paraná
2017
ABSTRACT Climate is the set of average atmospheric conditions that characterizes a region. It directly influences majority human activities, especially agriculture. classification systems (CCSs) are important tools in study agriculture, enabling knowledge climatic characteristics Thus, we aimed to perform characterization State Paraná using methods proposed by Köppen and Geiger (1928), modified Trewartha (1954) (KT), Thornthwaite (1948) (TH) Camargo (1991) Maluf (2000) (CM), data from...
Machine learning (ML) and its branch, deep (DL), is rapidly evolving gaining popularity as it outperforms other, more traditional methods in different areas of agriculture. However, ML DL techniques must be correctly applied to a problem produce an acceptable solution. This article provides guidelines for using with case study models/methods forecast yields cereals; some the concepts presented here are also applicable broadly. The objective provide clarity new users around use solve...
Abstract During the past few decades, a range of digital strategies for Nitrogen (N) management using various types input data and recommendation frameworks have been developed. Despite much research, benefits accrued from such technology equivocal. In this work, thirteen methods mid-season N recommendations in cereal production systems were evaluated simultaneously, ranging simple mass balance through to non-mechanistic approaches based on machine learning. To achieve this, an extensive...
The development of cost-effective, digitally based decision support systems is a key challenge in the optimization farm management. Yet, majority sensor-based tools which fertiliser management have relied on simplistic mechanistic frameworks normally informed by single sensor. This study used 20-year nitrogen (N) experiment winter wheat (Triticum aestivum L.) to test range approaches for N systems, including commercial options and novel, multivariate, data-driven approach. latter was...
Abstract Recognition of the importance soil moisture information to optimisation water-limited dryland cereal production has led Australian growers being encouraged make use sensors. However, irrespective merits different sensing technologies, only a small volume is sensed, raising questions as utility such sensors in broadacre cropping, especially given spatial variability water holding capacity. Here, using data collected from contrasting sites South Australia and Western over two seasons,...
Abstract. In-season, pre-harvest crop yield forecasts are essential for enhancing transparency in commodity markets and improving food security. They play a key role increasing resilience to climate change extreme events thus contribute the United Nations’ Sustainable Development Goal 2 of zero hunger. Pre-harvest forecasting is complex task, as several interacting factors formation, including in-season weather variability, events, long-term change, soil, pests, diseases farm management...
In the last decades, several methodologies for estimating crop phenology based on remote sensing data have been developed and used to create different algorithms. Although many studies conducted evaluate methodologies, a comprehensive understanding of potential current algorithms detect changes in growing season is still lacking, especially large regions with more than one per season. Therefore, this work aimed phenological metrics extraction methodologies. Using from over 1500 fields...
Accurate and timely regional estimates of agricultural production are key for decision makers. This study aims to understand how different machine learning techniques impact soybean yield estimation in extracting maximum information from remotely sensed MODIS enhanced vegetation index (EVI) that is constrained by phenology. Specifically, a methodology developed incorporating phenological aligned with EVI acquisition each pixel selecting the most significant predictors out 36 using feature...
Brazilian farming influences directly the worldwide economy. Thus, fast and reliable information on areas sown with main crops is essential for planning logistics public or private commodity market policies. Recent practices have embraced remote sensing to provide dynamics. Medium-to-low resolution free orbital images, such as those from Landsat 8 Sentinel 2, been used crop mapping; however, satellite image processing requires high computing power, especially when monitoring vast areas....
Knowledge of the agricultural calendar crops is essential to better estimate and forecast cultivation large-scale crops. The aim this study was sowing date (SD), maximum vegetative development (DMVD), harvest (HD) soybean corn in state Paraná, Brazil. Dates from 120 farms Enhanced Vegetation Index (EVI) Moderate Resolution Imaging Spectroradiometer (MODIS) 2011 2014 were used into a seasonal trend analysis obtain patterns. results indicate that majority sown during October DMVD occurs...
Processed-based models are increasingly being used with gridded soil and weather data; however, their validation is often on small, sampled datasets, calling into question accuracy when extrapolated to larger scales more uncertain input data. Here, we benchmarked the of APSIM Next Generation (APSIM-NG) crop model for wheat yield predictions multiple trials from 2005 2022 using data largest independently coordinated national trial network in world (Australia's Grain Research Development...
Mathematical modellers, decision support developers, statisticians, and students evaluate the differences between observed model predicted values. When evaluating models, it is far too easy to conduct evaluation by fitting a linear regression data. In this paper, steps are presented on ‘how to’ using deviance metrics rather than reporting r2 from regression. The paper aims provide sound reasoning, with data, against r2. addresses five arguments, previously put forward, for not when...
Due to the difficulty in discriminating soybean and corn mappings obtained by time series of satellite images, this study aimed apply data mining techniques separate corn. Pure pixels selection from Landsat-8 were extracted used build a standard spectro-temporal EVI profile for both crops. These profiles with Timesat software and, further incorporated Weka software. Five out eleven variables each crop found through decision tree, technique. five sufficient achieve separation crops an...
The knowledge of Sowing Dates (SD), Maximum Vegetative Development (MVDD), and Harvest (HD) crops is important for estimating forecasting large-scale productivity. Prior information on harvest date also useful in optimizing grain reception logistics improving business decision-making agro-industrial companies. This study aimed to develop a method predict the HD soybeans from MVDD, which was obtained crop maps state Paraná between 2011/2012 2013/2014 years. TIMESAT software used perform...
The prevalence of agro-meteorological data for specific regions serve as parameters agricultural and related climate studies. This study aims to regionalize the rainfall in State Parana (Southern Brazil) through mining techniques with ECMWF (European Centre Medium Range Weather Forecasts) from 1989 2013. algorithms k-means Simple EM (Expectation Maximization) clustering were applied Weka software, version 3.6. quality was determined J48 classification algorithm using training set. decision...
O estado do Parana ocupa uma posicao importante no cenario nacional na producao de soja, sendo responsavel por mais 18% da brasileira, produzindo que o quarto maior produtor mundial, a China. Para monitorar agricola, informacao area e fundamental neste processo. Diversas tecnicas metodos podem ser empregados, incluindo algoritmos Aprendizado Maquina ( Machine Learning) . Logo, este trabalho tem como objetivo comparar quatro aprendizado maquina para mapear soja partir imagens sensor Landsat-8...
RESUMO Na análise de dados espaciais em agricultura, a presença pontos influentes pode alterar consideravelmente os resultados das análises dependência espacial e, consequentemente, construção dos mapas. Quando se referem atributos físico-químicos do solo e da produtividade, mapas devem representar uma estimativa eficiente condições reais campo, já que são importantes informações utilizadas para manutenção um sistema agrícola manejo localizado, com otimização aplicação insumos agrícolas,...
Accurate field boundary delineation is a critical challenge in digital agriculture, impacting everything from crop monitoring to resource management. Existing methods often struggle with noise and fail generalize across varied landscapes, particularly when dealing cloud cover optical remote sensing. In response, this study presents new approach that leverages time series data Sentinel-2 (S2) Sentinel-1 (S1) imagery improve performance under diverse conditions, without the need for manual...