Development of low-cost remote sensing tools and methods for supporting smallholder agriculture

Cucho‐Padin, Gonzalo; Loayza, Hildo; Palacios, Susan; Balcazar, Mario; Carbajal, M.; Quíroz, Roberto

doi:10.1007/s12518-019-00292-5

Cited by 40 publications

(26 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They were geometrically corrected using control points on the ground and libraries of the QGIS 3.8 platform (QGIS Development Team, 2019). The NDVI values were represented by the mean of each plot, whereas CC was computed following a segmentation process between soil and vegetation considering a threshold value on soil adjusted vegetation index (SAVI), for more details see Cucho-Padin et al [69].…”

Section: Plant Materials and Experimental Designmentioning

confidence: 99%

Radiation Interception, Conversion and Partitioning Efficiency in Potato Landraces: How Far Are We from the Optimum?

Silva-Díaz

Ramírez

Rinza

et al. 2020

Plants

Self Cite

View full text Add to dashboard Cite

Crop efficiencies associated with intercepted radiation, conversion into biomass and allocation to edible organs are essential for yield improvement strategies that would enhance genetic properties to maximize carbon gain without increasing crop inputs. The production of 20 potato landraces—never studied before—was analyzed for radiation interception ( ε i ), conversion ( ε c ) and partitioning ( ε p ) efficiencies. Additionally, other physiological traits related to senescence delay (normalized difference vegetation index (NDVI) s l p ), tuberization precocity ( t u ), photosynthetic performance and dry tuber yield per plant (TY) were also assessed. Vegetation reflectance was remotely acquired and the efficiencies estimated through a process-based model parameterized by a time-series of airborne imageries. The combination of ε i and ε c , closely associated with an early tuber maturity and a NDVI s l p explained 39% of the variability grouping the most productive genotypes. TY was closely correlated to senescence delay (r P e a r s o n = 0.74), indicating the usefulness of remote sensing methods for potato yield diversity characterization. About 89% of TY was explained by the first three principal components, associated mainly to t u , ε c and ε i , respectively. When comparing potato with other major crops, its ε p is very close to the theoretical maximum. These findings suggest that there is room for improving ε i and ε c to enhance potato production.

show abstract

Section: Plant Materials and Experimental Designmentioning

confidence: 99%

Radiation Interception, Conversion and Partitioning Efficiency in Potato Landraces: How Far Are We from the Optimum?

Silva-Díaz

Ramírez

Rinza

et al. 2020

Plants

Self Cite

View full text Add to dashboard Cite

show abstract

“…The models and experiments were evaluated using standard statistical analysis, i.e., confusion matrix, cross-validation, overall accuracy, precision, recall, F1-Score, and McNemar's test [50,51]. These statistical measures have been used to evaluate different machine learning algorithms, such examples include, but are not limited to, Petropoulos et al [52], Tong et al [53], and Cucho-Padin et al [54].…”

Section: Accuracy Assessment and Smallholder Maize Area Estimationmentioning

confidence: 99%

Mapping Smallholder Maize Farms Using Multi-Temporal Sentinel-1 Data in Support of the Sustainable Development Goals

2021

View full text Add to dashboard Cite

Reducing food insecurity in developing countries is one of the crucial targets of the Sustainable Development Goals (SDGs). Smallholder farmers play a crucial role in combating food insecurity. However, local planning agencies and governments do not have adequate spatial information on smallholder farmers, and this affects the monitoring of the SDGs. This study utilized Sentinel-1 multi-temporal data to develop a framework for mapping smallholder maize farms and to estimate maize production area as a parameter for supporting the SDGs. We used Principal Component Analysis (PCA) to pixel fuse the multi-temporal data to only three components for each polarization (vertical transmit and vertical receive (VV), vertical transmit and horizontal receive (VH), and VV/VH), which explained more than 70% of the information. The Support Vector Machine (SVM) and Extreme Gradient Boosting (Xgboost) algorithms were used at model-level feature fusion to classify the data. The results show that the adopted strategy of two-stage image fusion was sufficient to map the distribution and estimate production areas for smallholder farms. An overall accuracy of more than 90% for both SVM and Xgboost algorithms was achieved. There was a 3% difference in production area estimation observed between the two algorithms. This framework can be used to generate spatial agricultural information in areas where agricultural survey data are limited and for areas that are affected by cloud coverage. We recommend the use of Sentinel-1 multi-temporal data in conjunction with machine learning algorithms to map smallholder maize farms to support the SDGs.

show abstract

“…In relation to our problems and our constraints, we choose to focus on the solution which is the most open-source and our choice therefore fall on Ardupilot. This autopilot has also proven operational in different environments as we find it in application on, of course, aerial vehicles (UAV) (Wardihani et al, 2018, Fawcett et al, 2019, Melo et al, 2017, Carlson, Rysgaard, 2018, Cucho-Padin et al, 2019, Washburn et al, 2017, but also on ground vehicles (UGV) (Velaskar et al, 2014) or surface vehicles (USV) (Sinisterra et al, 2017, Moulton et al, 2018, Raber, Schill, 2019 and even on underwater vehicles (UUV) (Schillaci et al, 2017, Luo et al, 2019, Sani et al, 2019…”

Section: Open-source Autopilots For Diverse Environmentsmentioning

confidence: 99%

Porting Ardupilot to Esp32: Towards a Universal Open-Source Architecture for Agile and Easily Replicable Multi-Domains Mapping Robots

Beaudoin

Avanthey

Villard

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this article, we are interested in the implementation of an open-source low-level architecture (critical system) adapted to agile and easily replicable close-range remote sensing robots operating in multiple evolution domains. After reviewing the existing autopilots responding to these needs, we discuss the available hardware solutions and their limits. Then, we propose an original solution (software and hardware) that we developed to obtain a universal low-level architecture for all our exploration robots, whatever their environment of evolution, and the steps needed to make it run on our chosen family of micro-controllers: the ESP32. Finally, we present the operational results obtained on our different platforms (land, surface, submarine and air), their limits and the envisaged perspectives.

show abstract

Development of low-cost remote sensing tools and methods for supporting smallholder agriculture

Cited by 40 publications

References 32 publications

Radiation Interception, Conversion and Partitioning Efficiency in Potato Landraces: How Far Are We from the Optimum?

Radiation Interception, Conversion and Partitioning Efficiency in Potato Landraces: How Far Are We from the Optimum?

Mapping Smallholder Maize Farms Using Multi-Temporal Sentinel-1 Data in Support of the Sustainable Development Goals

Porting Ardupilot to Esp32: Towards a Universal Open-Source Architecture for Agile and Easily Replicable Multi-Domains Mapping Robots

Contact Info

Product

Resources

About