This page has only limited features, please log in for full access.

Dr. Francois Waldner
CSIRO

Basic Info


Research Keywords & Expertise

0 Agriculture
0 Data Analytics
0 Machine Learning
0 Remote Sensing
0 Time Series Analysis

Fingerprints

Remote Sensing
Agriculture
Machine Learning
Data Analytics

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 18 August 2021 in Sustainability
Reads 0
Downloads 0

Many private and public actors are incentivized by the promises of big data technologies: digital tools underpinned by capabilities like artificial intelligence and machine learning. While many shared value propositions exist regarding what these technologies afford, public-facing concerns related to individual privacy, algorithm fairness, and the access to insights requires attention if the widespread use and subsequent value of these technologies are to be fully realized. Drawing from perspectives of data science, social science and technology acceptance, we present an interdisciplinary analysis that links these concerns with traditional research and development (R&D) activities. We suggest a reframing of the public R&D ‘brand’ that responds to legitimate concerns related to data collection, development, and the implementation of big data technologies. We offer as a case study Australian agriculture, which is currently undergoing such digitalization, and where concerns have been raised by landholders and the research community. With seemingly limitless possibilities, an updated account of responsible R&D in an increasingly digitalized world may accelerate the ways in which we might realize the benefits of big data and mitigate harmful social and environmental costs.

ACS Style

Cara Stitzlein; Simon Fielke; François Waldner; Todd Sanderson. Reputational Risk Associated with Big Data Research and Development: An Interdisciplinary Perspective. Sustainability 2021, 13, 9280 .

AMA Style

Cara Stitzlein, Simon Fielke, François Waldner, Todd Sanderson. Reputational Risk Associated with Big Data Research and Development: An Interdisciplinary Perspective. Sustainability. 2021; 13 (16):9280.

Chicago/Turabian Style

Cara Stitzlein; Simon Fielke; François Waldner; Todd Sanderson. 2021. "Reputational Risk Associated with Big Data Research and Development: An Interdisciplinary Perspective." Sustainability 13, no. 16: 9280.

Journal article
Published: 04 June 2021 in Remote Sensing
Reads 0
Downloads 0

Digital agriculture services can greatly assist growers to monitor their fields and optimize their use throughout the growing season. Thus, knowing the exact location of fields and their boundaries is a prerequisite. Unlike property boundaries, which are recorded in local council or title records, field boundaries are not historically recorded. As a result, digital services currently ask their users to manually draw their field, which is time-consuming and creates disincentives. Here, we present a generalized method, hereafter referred to as DECODE (DEtect, COnsolidate, and DElinetate), that automatically extracts accurate field boundary data from satellite imagery using deep learning based on spatial, spectral, and temporal cues. We introduce a new convolutional neural network (FracTAL ResUNet) as well as two uncertainty metrics to characterize the confidence of the field detection and field delineation processes. We finally propose a new methodology to compare and summarize field-based accuracy metrics. To demonstrate the performance and scalability of our method, we extracted fields across the Australian grains zone with a pixel-based accuracy of 0.87 and a field-based accuracy of up to 0.88 depending on the metric. We also trained a model on data from South Africa instead of Australia and found it transferred well to unseen Australian landscapes. We conclude that the accuracy, scalability and transferability of DECODE shows that large-scale field boundary extraction based on deep learning has reached operational maturity. This opens the door to new agricultural services that provide routine, near-real time field-based analytics.

ACS Style

François Waldner; Foivos Diakogiannis; Kathryn Batchelor; Michael Ciccotosto-Camp; Elizabeth Cooper-Williams; Chris Herrmann; Gonzalo Mata; Andrew Toovey. Detect, Consolidate, Delineate: Scalable Mapping of Field Boundaries Using Satellite Images. Remote Sensing 2021, 13, 2197 .

AMA Style

François Waldner, Foivos Diakogiannis, Kathryn Batchelor, Michael Ciccotosto-Camp, Elizabeth Cooper-Williams, Chris Herrmann, Gonzalo Mata, Andrew Toovey. Detect, Consolidate, Delineate: Scalable Mapping of Field Boundaries Using Satellite Images. Remote Sensing. 2021; 13 (11):2197.

Chicago/Turabian Style

François Waldner; Foivos Diakogiannis; Kathryn Batchelor; Michael Ciccotosto-Camp; Elizabeth Cooper-Williams; Chris Herrmann; Gonzalo Mata; Andrew Toovey. 2021. "Detect, Consolidate, Delineate: Scalable Mapping of Field Boundaries Using Satellite Images." Remote Sensing 13, no. 11: 2197.

Corrigendum
Published: 10 March 2021 in Environmental Research Letters
Reads 0
Downloads 0
ACS Style

Z Hochman; F Waldner. Corrigendum: Simplicity on the far side of complexity: optimizing nitrogen for wheat in increasingly variable rainfall environments (2020 Environ. Res. Lett. 15 114060). Environmental Research Letters 2021, 16, 049501 .

AMA Style

Z Hochman, F Waldner. Corrigendum: Simplicity on the far side of complexity: optimizing nitrogen for wheat in increasingly variable rainfall environments (2020 Environ. Res. Lett. 15 114060). Environmental Research Letters. 2021; 16 (4):049501.

Chicago/Turabian Style

Z Hochman; F Waldner. 2021. "Corrigendum: Simplicity on the far side of complexity: optimizing nitrogen for wheat in increasingly variable rainfall environments (2020 Environ. Res. Lett. 15 114060)." Environmental Research Letters 16, no. 4: 049501.

Journal article
Published: 01 November 2020 in Environmental Research Letters
Reads 0
Downloads 0
ACS Style

Z Hochman; F Waldner. Simplicity on the far side of complexity: optimizing nitrogen for wheat in increasingly variable rainfall environments. Environmental Research Letters 2020, 15, 114060 .

AMA Style

Z Hochman, F Waldner. Simplicity on the far side of complexity: optimizing nitrogen for wheat in increasingly variable rainfall environments. Environmental Research Letters. 2020; 15 (11):114060.

Chicago/Turabian Style

Z Hochman; F Waldner. 2020. "Simplicity on the far side of complexity: optimizing nitrogen for wheat in increasingly variable rainfall environments." Environmental Research Letters 15, no. 11: 114060.

Preprint content
Published: 03 September 2020
Reads 0
Downloads 0

Many private and public actors are incentivized by big data technologies: digital tools underpinned by capabilities such as artificial intelligence and machine learning. While many shared value propositions exist about what these technologies afford, public facing concerns related to individual privacy, algorithm fairness, and access to insights require attention if the widespread use and subsequent value of these technologies are to be fully realized. Drawing from perspectives of data science, social science and technology acceptance, we present an interdisciplinary analysis that reveals the connections between these concerns and traditional research and development (R&D) activities of data collection, technology development and implementation. Given the behaviors associated with digital transformation opportunities, we suggest a reframing of the public-facing R&D ‘brand’ that responds to legitimate concerns related to individual privacy, fairness, and social equity. We offer as a case study Australian agriculture, which is currently undergoing such digitalisation and where concerns have been raised by landholders and the research community. With seemingly limitless possibilities, an updated account of responsible R&D in an increasing digitalized world may accelerate how we might realize benefits of big data and mitigate harmful social and environmental costs.

ACS Style

Cara Stitzlein; Simon Fielke; François Waldner; Todd Sanderson. Managing reputational risk associated with big data research and development: an interdisciplinary perspective. 2020, 1 .

AMA Style

Cara Stitzlein, Simon Fielke, François Waldner, Todd Sanderson. Managing reputational risk associated with big data research and development: an interdisciplinary perspective. . 2020; ():1.

Chicago/Turabian Style

Cara Stitzlein; Simon Fielke; François Waldner; Todd Sanderson. 2020. "Managing reputational risk associated with big data research and development: an interdisciplinary perspective." , no. : 1.

Letter
Published: 03 August 2020 in Remote Sensing
Reads 0
Downloads 0

In remote sensing, the term accuracy typically expresses the degree of correctness of a map. Best practices in accuracy assessment have been widely researched and include guidelines on how to select validation data using probability sampling designs. In practice, however, probability samples may be lacking and, instead, cross-validation using non-probability samples is common. This practice is risky because the resulting accuracy estimates can easily be mistaken for map accuracy. The following question arises: to what extent are accuracy estimates obtained from non-probability samples representative of map accuracy? This letter introduces the T index to answer this question. Certain cross-validation designs (such as the common single-split or hold-out validation) provide representative accuracy estimates when hold-out sets are simple random samples of the map population. The T index essentially measures the probability of a hold-out set of unknown sampling design to be a simple random sample. To that aim, we compare its spread in the feature space against the spread of random unlabelled samples of the same size. Data spread is measured by a variant of Moran’s I autocorrelation index. Consistent interpretation of the T index is proposed through the prism of significance testing, with T values < 0.05 indicating unreliable accuracy estimates. Its relevance and interpretation guidelines are also illustrated in a case study on crop-type mapping. Uptake of the T index by the remote-sensing community will help inform about—and sometimes caution against—the representativeness of accuracy estimates obtained by cross-validation, so that users can better decide whether a map is fit for their purpose or how its accuracy impacts their application. Subsequently, the T index will build trust and improve the transparency of accuracy assessment in conditions which deviate from best practices.

ACS Style

François Waldner. The T Index: Measuring the Reliability of Accuracy Estimates Obtained from Non-Probability Samples. Remote Sensing 2020, 12, 2483 .

AMA Style

François Waldner. The T Index: Measuring the Reliability of Accuracy Estimates Obtained from Non-Probability Samples. Remote Sensing. 2020; 12 (15):2483.

Chicago/Turabian Style

François Waldner. 2020. "The T Index: Measuring the Reliability of Accuracy Estimates Obtained from Non-Probability Samples." Remote Sensing 12, no. 15: 2483.

Journal article
Published: 21 May 2020 in Remote Sensing
Reads 0
Downloads 0

The onus for monitoring crop growth from space is its ability to be applied anytime and anywhere, to produce crop yield estimates that are consistent at both the subfield scale for farming management strategies and the country level for national crop yield assessment. Historically, the requirements for satellites to successfully monitor crop growth and yield differed depending on the extent of the area being monitored. Diverging imaging capabilities can be reconciled by blending images from high-temporal-frequency (HTF) and high-spatial-resolution (HSR) sensors to produce images that possess both HTF and HSR characteristics across large areas. We evaluated the relative performance of Moderate Resolution Imaging Spectroradiometer (MODIS), Landsat, and blended imagery for crop yield estimates (2009–2015) using a carbon-turnover yield model deployed across the Australian cropping area. Based on the fraction of missing Landsat observations, we further developed a parsimonious framework to inform when and where blending is beneficial for nationwide crop yield prediction at a finer scale (i.e., the 25-m pixel resolution). Landsat provided the best yield predictions when no observations were missing, which occurred in 17% of the cropping area of Australia. Blending was preferred when

ACS Style

Yang Chen; Tim R. McVicar; Randall J. Donohue; Nikhil Garg; François Waldner; Noboru Ota; Lingtao Li; Roger Lawes. To Blend or Not to Blend? A Framework for Nationwide Landsat–MODIS Data Selection for Crop Yield Prediction. Remote Sensing 2020, 12, 1653 .

AMA Style

Yang Chen, Tim R. McVicar, Randall J. Donohue, Nikhil Garg, François Waldner, Noboru Ota, Lingtao Li, Roger Lawes. To Blend or Not to Blend? A Framework for Nationwide Landsat–MODIS Data Selection for Crop Yield Prediction. Remote Sensing. 2020; 12 (10):1653.

Chicago/Turabian Style

Yang Chen; Tim R. McVicar; Randall J. Donohue; Nikhil Garg; François Waldner; Noboru Ota; Lingtao Li; Roger Lawes. 2020. "To Blend or Not to Blend? A Framework for Nationwide Landsat–MODIS Data Selection for Crop Yield Prediction." Remote Sensing 12, no. 10: 1653.

Journal article
Published: 20 May 2020 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

A precise knowledge of the crop distribution in the landscape is crucial for the agricultural sector to inform better management and logistics. Crop-type maps are often derived by the supervised classification of satellite imagery using machine learning models. The choice of data sampled during the data collection phase of building a classification model has a tremendous impact on a model's performance, and is usually collected via roadside surveys throughout the area of interest. However, the large spatial extent, and the varying accessibility to fields, often makes the acquisition of appropriate training data sets difficult. As such, in situ data are often collected on a best-effort basis, leading to inefficiencies, sub-optimal accuracies, and unnecessarily large sample sizes. This highlights the need for new more efficient tools to guide data collection. Here, we address three tasks that one commonly faces when planning to collect in situ data: which survey route to select among a set logistically feasible routes; which fields are the most relevant to collect along the chosen survey route; and how to best augment existing in situ data sets with additional observations. Our findings show that the normalised Moran's I index is a useful indicator for choosing the survey route, and that sequential exploration methods can identify the most important fields to survey on that route. The provided recommendations are flexible, overcome the main logistical constraints associated with in situ data collection, yield accurate results, and could be incorporated in a mobile application to assist data collection in real-time.

ACS Style

Jared Fowler; François Waldner; Zvi Hochman. All pixels are useful, but some are more useful: Efficient in situ data collection for crop-type mapping using sequential exploration methods. International Journal of Applied Earth Observation and Geoinformation 2020, 91, 102114 .

AMA Style

Jared Fowler, François Waldner, Zvi Hochman. All pixels are useful, but some are more useful: Efficient in situ data collection for crop-type mapping using sequential exploration methods. International Journal of Applied Earth Observation and Geoinformation. 2020; 91 ():102114.

Chicago/Turabian Style

Jared Fowler; François Waldner; Zvi Hochman. 2020. "All pixels are useful, but some are more useful: Efficient in situ data collection for crop-type mapping using sequential exploration methods." International Journal of Applied Earth Observation and Geoinformation 91, no. : 102114.

Journal article
Published: 19 May 2020 in Remote Sensing of Environment
Reads 0
Downloads 0

Applications of digital agricultural services often require either farmers or their advisers to provide digital records of their field boundaries. Automatic extraction of field boundaries from satellite imagery would reduce the reliance on manual input of these records, which is time consuming, and would underpin the provision of remote products and services. The lack of current field boundary data sets seems to indicate low uptake of existing methods, presumably because of expensive image preprocessing requirements and local, often arbitrary, tuning. In this paper, we propose a data-driven, robust and general method to facilitate field boundary extraction from satellite images. We formulated this task as a multi-task semantic segmentation problem. We used ResUNet-a, a deep convolutional neural network with a fully connected UNet backbone that features dilated convolutions and conditioned inference to identify: 1) the extent of fields; 2) the field boundaries; and 3) the distance to the closest boundary. By asking the algorithm to reconstruct three correlated outputs, the model's performance and its ability to generalise greatly improve. Segmentation of individual fields was then achieved by post-processing the three model outputs, e.g., via thresholding or watershed segmentation. Using a single monthly composite image from Sentinel-2 as input, our model was highly accurate in mapping field extent, field boundaries and, consequently, individual fields. Replacing the monthly composite with a single-date image close to the compositing period marginally decreased accuracy. We then showed in a series of experiments that, without recalibration, the same model generalised well across resolutions (10 m to 30 m), sensors (Sentinel-2 to Landsat-8), space and time. Building consensus by averaging model predictions from at least four images acquired across the season is paramount to reducing the temporal variations of accuracy. Our convolutional neural network is capable of learning complex hierarchical contextual features from the image to accurately detect field boundaries and discard irrelevant boundaries, thereby outperforming conventional edge filters. By minimising over-fitting and image preprocessing requirements, and by replacing local arbitrary decisions by data-driven ones, our approach is expected to facilitate the extraction of individual crop fields at scale.

ACS Style

François Waldner; Foivos Diakogiannis. Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote Sensing of Environment 2020, 245, 111741 .

AMA Style

François Waldner, Foivos Diakogiannis. Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote Sensing of Environment. 2020; 245 ():111741.

Chicago/Turabian Style

François Waldner; Foivos Diakogiannis. 2020. "Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network." Remote Sensing of Environment 245, no. : 111741.

Journal article
Published: 23 April 2020 in Remote Sensing
Reads 0
Downloads 0

Fallows are widespread in dryland cropping systems. However, timely information about their spatial extent and location remains scarce. To overcome this lack of information, we propose to classify fractional cover data from Sentinel-2 with biased support vector machines. Fractional cover images describe the land surface in intuitive, biophysical terms, which reduces the spectral variability within the fallow class. Biased support vector machines are a type of one-class classifiers that require labelled data for the class of interest and unlabelled data for the other classes. They allow us to extrapolate in-situ observations collected during flowering to the rest of the growing season to generate large training data sets, thereby reducing the data collection requirements. We tested this approach to monitor fallows in the northern grains region of Australia and showed that the seasonal fallow extent can be mapped with >92% accuracy both during the summer and winter seasons. The summer fallow extent can be accurately mapped as early as mid-December (1–4 months before harvest). The winter fallow extent can be accurately mapped from mid-August (2–4 months before harvest). Our method also detected emergence dates successfully, indicating the near real-time accuracy of our method. We estimated that the extent of fallow fields across the northern grains region of Australia ranged between 50% in winter 2017 and 85% in winter 2019. Our method is scalable, sensor independent and economical to run. As such, it lays the foundations for reconstructing and monitoring the cropping dynamics in Australia.

ACS Style

Liya Zhao; François Waldner; Peter Scarth; Benjamin Mack; Zvi Hochman. Combining Fractional Cover Images with One-Class Classifiers Enables Near Real-Time Monitoring of Fallows in the Northern Grains Region of Australia. Remote Sensing 2020, 12, 1337 .

AMA Style

Liya Zhao, François Waldner, Peter Scarth, Benjamin Mack, Zvi Hochman. Combining Fractional Cover Images with One-Class Classifiers Enables Near Real-Time Monitoring of Fallows in the Northern Grains Region of Australia. Remote Sensing. 2020; 12 (8):1337.

Chicago/Turabian Style

Liya Zhao; François Waldner; Peter Scarth; Benjamin Mack; Zvi Hochman. 2020. "Combining Fractional Cover Images with One-Class Classifiers Enables Near Real-Time Monitoring of Fallows in the Northern Grains Region of Australia." Remote Sensing 12, no. 8: 1337.

Journal article
Published: 21 February 2020 in ISPRS Journal of Photogrammetry and Remote Sensing
Reads 0
Downloads 0

Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications. Due to the large within-class and small between-class variance in pixel values of objects of interest, this remains a challenging task. In recent years, deep convolutional neural networks have started being used in remote sensing applications and demonstrate state of the art performance for pixel level classification of objects. Here we propose a reliable framework for performant results for the task of semantic segmentation of monotemporal very high resolution aerial images. Our framework consists of a novel deep learning architecture, ResUNet-a, and a novel loss function based on the Dice loss. ResUNet-a uses a UNet encoder/decoder backbone, in combination with residual connections, atrous convolutions, pyramid scene parsing pooling and multi-tasking inference. ResUNet-a infers sequentially the boundary of the objects, the distance transform of the segmentation mask, the segmentation mask and a colored reconstruction of the input. Each of the tasks is conditioned on the inference of the previous ones, thus establishing a conditioned relationship between the various tasks, as this is described through the architecture’s computation graph. We analyse the performance of several flavours of the Generalized Dice loss for semantic segmentation, and we introduce a novel variant loss function for semantic segmentation of objects that has excellent convergence properties and behaves well even under the presence of highly imbalanced classes. The performance of our modeling framework is evaluated on the ISPRS 2D Potsdam dataset. Results show state-of-the-art performance with an average F1 score of 92.9% over all classes for our best model.

ACS Style

Foivos I. Diakogiannis; Francois Waldner; Peter Caccetta; Chen Wu. ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing 2020, 162, 94 -114.

AMA Style

Foivos I. Diakogiannis, Francois Waldner, Peter Caccetta, Chen Wu. ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing. 2020; 162 ():94-114.

Chicago/Turabian Style

Foivos I. Diakogiannis; Francois Waldner; Peter Caccetta; Chen Wu. 2020. "ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data." ISPRS Journal of Photogrammetry and Remote Sensing 162, no. : 94-114.

Journal article
Published: 01 February 2020 in ISPRS Journal of Photogrammetry and Remote Sensing
Reads 0
Downloads 0
ACS Style

Elisa Kamir; Francois Waldner; Zvi Hochman. Estimating wheat yields in Australia using climate records, satellite image time series and machine learning methods. ISPRS Journal of Photogrammetry and Remote Sensing 2020, 160, 124 -135.

AMA Style

Elisa Kamir, Francois Waldner, Zvi Hochman. Estimating wheat yields in Australia using climate records, satellite image time series and machine learning methods. ISPRS Journal of Photogrammetry and Remote Sensing. 2020; 160 ():124-135.

Chicago/Turabian Style

Elisa Kamir; Francois Waldner; Zvi Hochman. 2020. "Estimating wheat yields in Australia using climate records, satellite image time series and machine learning methods." ISPRS Journal of Photogrammetry and Remote Sensing 160, no. : 124-135.

Journal article
Published: 11 January 2020 in Remote Sensing
Reads 0
Downloads 0

Reference data collected to validate land-cover maps are generally considered free of errors. In practice, however, they contain errors despite best efforts to minimize them. These errors propagate during accuracy assessment and tweak the validation results. For photo-interpreted reference data, the two most widely studied sources of error are systematic incorrect labeling and vigilance drops. How estimation errors, i.e., errors intrinsic to the response design, affect the accuracy of reference data is far less understood. In this paper, we analyzed the impact of estimation errors for two types of classification systems (binary and multiclass) as well as for two common response designs (point-based and partition-based) with a range of sub-sample sizes. Our quantitative results indicate that labeling errors due to proportion estimations should not be neglected. They further confirm that the accuracy of response designs depends on the class proportions within the sampling units, with complex landscapes being more prone to errors. As a result, response designs where the number of sub-samples is predefined and fixed are inefficient. To guarantee high accuracy standards of validation data with minimum data collection effort, we propose a new method to adapt the number of sub-samples for each sample during the validation process. In practice, sub-samples are incrementally selected and labeled until the estimated class proportions reach the desired level of confidence. As a result, less effort is spent on labeling univocal cases and the spared effort can be allocated to more ambiguous cases. This increases the reliability of reference data and of subsequent accuracy assessment. Across our study site, we demonstrated that such an approach could reduce the labeling effort by 50% to 75%, with greater gains in homogeneous landscapes. We contend that adopting this optimization approach will not only increase the efficiency of reference data collection, but will also help deliver more reliable accuracy estimates to the user community.

ACS Style

Julien Radoux; François Waldner; Patrick Bogaert. How Response Designs and Class Proportions Affect the Accuracy of Validation Data. Remote Sensing 2020, 12, 257 .

AMA Style

Julien Radoux, François Waldner, Patrick Bogaert. How Response Designs and Class Proportions Affect the Accuracy of Validation Data. Remote Sensing. 2020; 12 (2):257.

Chicago/Turabian Style

Julien Radoux; François Waldner; Patrick Bogaert. 2020. "How Response Designs and Class Proportions Affect the Accuracy of Validation Data." Remote Sensing 12, no. 2: 257.

Journal article
Published: 26 December 2019 in Agricultural and Forest Meteorology
Reads 0
Downloads 0

There is considerable demand for nationwide grain yield estimation during the cropping season by growers, grain marketers, grain handlers, agricultural businesses, and market brokers. In this paper, we developed a semi-empirical model (Crop-SI) to estimate the yield of the three major crops in the dryland Australian wheatbelt by combining a radiation use efficiency approach with meteorology driven Stress Indices (SI) at critical crop growth stages (e.g., anthesis and grain filling). These crop-specific SI (e.g., drought, heat and cold stress) help explain the impact of high spatial agro-environmental heterogeneity, which lead to substantial improvement in grain yield prediction. Crop-SI explains 87%, 69% and 83% of the observed field-scale grain yield variability with root mean square error of ~0.4, 0.4 and 0.5 t/ha for canola, wheat, and barley, respectively. At the pixel-level, Crop-SI reduces the relative error in grain yield estimation to 34%, 25%, and 20% for canola, wheat, barley, respectively, compared to two benchmark models. By incorporating water- and temperature-driven stresses, Crop-SI's predictive skill in highly variable environments is enhanced. As such, it paves the way for the next generation of agricultural systems models, knowledge products and decision support tools that need to operate at various scales.

ACS Style

Yang Chen; Randall J. Donohue; Tim McVicar; François Waldner; Gonzalo Mata; Noboru Ota; Alireza Houshmandfar; Kavina Dayal; Roger Lawes. Nationwide crop yield estimation based on photosynthesis and meteorological stress indices. Agricultural and Forest Meteorology 2019, 284, 107872 .

AMA Style

Yang Chen, Randall J. Donohue, Tim McVicar, François Waldner, Gonzalo Mata, Noboru Ota, Alireza Houshmandfar, Kavina Dayal, Roger Lawes. Nationwide crop yield estimation based on photosynthesis and meteorological stress indices. Agricultural and Forest Meteorology. 2019; 284 ():107872.

Chicago/Turabian Style

Yang Chen; Randall J. Donohue; Tim McVicar; François Waldner; Gonzalo Mata; Noboru Ota; Alireza Houshmandfar; Kavina Dayal; Roger Lawes. 2019. "Nationwide crop yield estimation based on photosynthesis and meteorological stress indices." Agricultural and Forest Meteorology 284, no. : 107872.

Article
Published: 31 October 2019 in Scientific Reports
Reads 0
Downloads 0

Empirical yield estimation from satellite data has long lacked suitable combinations of spatial and temporal resolutions. Consequently, the selection of metrics, i.e., temporal descriptors that predict grain yield, has likely been driven by practicality and data availability rather than by systematic targetting of critically sensitive periods as suggested by knowledge of crop physiology. The current trend towards hyper-temporal data raises two questions: How does temporality affect the accuracy of empirical models? Which metrics achieve optimal performance? We followed an in silico approach based on crop modelling which can generate any observation frequency, explore a range of growing conditions and reduce the cost of measuring yields in situ. We simulated wheat crops across Australia and regressed six types of metrics derived from the resulting time series of Leaf Area Index (LAI) against wheat yields. Empirical models using advanced LAI metrics achieved national relevance and, contrary to simple metrics, did not benefit from the addition of weather information. This suggests that they already integrate most climatic effects on yield. Simple metrics remained the best choice when LAI data are sparse. As we progress into a data-rich era, our results support a shift towards metrics that truly harness the temporal dimension of LAI data.

ACS Style

François Waldner; Heidi Horan; Yang Chen; Zvi Hochman. High temporal resolution of leaf area data improves empirical estimation of grain yield. Scientific Reports 2019, 9, 1 -14.

AMA Style

François Waldner, Heidi Horan, Yang Chen, Zvi Hochman. High temporal resolution of leaf area data improves empirical estimation of grain yield. Scientific Reports. 2019; 9 (1):1-14.

Chicago/Turabian Style

François Waldner; Heidi Horan; Yang Chen; Zvi Hochman. 2019. "High temporal resolution of leaf area data improves empirical estimation of grain yield." Scientific Reports 9, no. 1: 1-14.

Preprint
Published: 26 October 2019
Reads 0
Downloads 0

Applications of digital agricultural services often require either farmers or their advisers to provide digital records of their field boundaries. Automatic extraction of field boundaries from satellite imagery would reduce the reliance on manual input of these records which is time consuming and error-prone, and would underpin the provision of remote products and services. The lack of current field boundary data sets seems to indicate low uptake of existing methods,presumably because of expensive image preprocessing requirements and local, often arbitrary, tuning. In this paper, we address the problem of field boundary extraction from satellite images as a multitask semantic segmentation problem. We used ResUNet-a, a deep convolutional neural network with a fully connected UNet backbone that features dilated convolutions and conditioned inference, to assign three labels to each pixel: 1) the probability of belonging to a field; 2) the probability of being part of a boundary; and 3) the distance to the closest boundary. These labels can then be combined to obtain closed field boundaries. Using a single composite image from Sentinel-2, the model was highly accurate in mapping field extent, field boundaries, and, consequently, individual fields. Replacing the monthly composite with a single-date image close to the compositing period only marginally decreased accuracy. We then showed in a series of experiments that our model generalised well across resolutions, sensors, space and time without recalibration. Building consensus by averaging model predictions from at least four images acquired across the season is the key to coping with the temporal variations of accuracy. By minimising image preprocessing requirements and replacing local arbitrary decisions by data-driven ones, our approach is expected to facilitate the extraction of individual crop fields at scale.

ACS Style

François Waldner; Foivos Diakogiannis. Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network. 2019, 1 .

AMA Style

François Waldner, Foivos Diakogiannis. Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network. . 2019; ():1.

Chicago/Turabian Style

François Waldner; Foivos Diakogiannis. 2019. "Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network." , no. : 1.

Journal article
Published: 20 September 2019 in Remote Sensing of Environment
Reads 0
Downloads 0

Most cropping systems around the world are organised around few dominant crops and a larger number of less frequent crops. While rare and infrequent crops occupy a small share of the cropped area, they produce ecological benefits on farmland, contribute to sustainability and help provide food and nutritional security. However, data about their location and extent derived from satellite imagery generally lack accuracy, largely owing to the class imbalance problem. Class imbalance occurs when only few instances of some classes are available for training classifiers, and leads to large error rates of the infrequent classes. In this study, we assessed the magnitude of the class imbalance problem in crop classification and evaluated balancing methods to combat it by creating synthetic minority observations or by removing majority observations. To that aim, we generated 18 unbalanced data sets from Sentinel-2 time series and crop type observations in Victoria, Australia. These data sets covered a wide range of complexity, number of classes, number of samples per class and spectral separability which enabled us to gather evidence about the benefits and drawbacks of balancing methods in various settings. Classification accuracy was assessed with two metrics: the Overall Accuracy (OA), which gives more weight to majority classes, and the G-Mean accuracy (GM), which is more sensitive to minority classes. Results showed that class imbalance explained near 40% of the accuracy variability. We found that balancing methods boosted GM by 0.01–0.54 but no single best solution emerged. The price for increasing the accuracy of minority classes was a drop in OA of a magnitude that was problem- and method-specific. We thus applied an algorithm selection method called the F-race to identify optimal balancing methods in a computationally economic fashion. Optimal balancing methods lead to maximum gain in GM and minimum loss in OA. We demonstrated that this approach either successfully identified optimal balancing methods or ones that were not significantly sub-optimal, while reducing the computational cost by up to 60%. It can readily be incorporated to operational crop classification systems with little disruption to the existing processing chains. This contribution paves the way for achieving a more comprehensive and detailed view of crop distribution and cropping sequences.

ACS Style

François Waldner; Yang Chen; Roger Lawes; Zvi Hochman. Needle in a haystack: Mapping rare and infrequent crops using satellite imagery and data balancing methods. Remote Sensing of Environment 2019, 233, 111375 .

AMA Style

François Waldner, Yang Chen, Roger Lawes, Zvi Hochman. Needle in a haystack: Mapping rare and infrequent crops using satellite imagery and data balancing methods. Remote Sensing of Environment. 2019; 233 ():111375.

Chicago/Turabian Style

François Waldner; Yang Chen; Roger Lawes; Zvi Hochman. 2019. "Needle in a haystack: Mapping rare and infrequent crops using satellite imagery and data balancing methods." Remote Sensing of Environment 233, no. : 111375.

Preprint content
Published: 01 May 2019
Reads 0
Downloads 0
ACS Style

François Waldner; Heidi Horan; Yang Chen; Zvi Hochman. High temporal resolution of leaf area data improves empirical estimation of grain yield. 2019, 1 .

AMA Style

François Waldner, Heidi Horan, Yang Chen, Zvi Hochman. High temporal resolution of leaf area data improves empirical estimation of grain yield. . 2019; ():1.

Chicago/Turabian Style

François Waldner; Heidi Horan; Yang Chen; Zvi Hochman. 2019. "High temporal resolution of leaf area data improves empirical estimation of grain yield." , no. : 1.

Journal article
Published: 16 April 2019 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Cropland maps derived from satellite imagery have become a common source of information to estimate food production, support land use policies, and measure the environmental impacts of agriculture. Cropland classification models are typically calibrated with data collected from roadside surveys which enable the sampling of large areas at a relatively low cost. However, there is a risk of providing biased data as environmental and management gradients may not be fully captured from road networks, thereby violating the assumption of representativeness of calibration data. Despite being widely adopted, the potential biases of roadside sampling have so far not been thoroughly addressed. In this study, we looked for evidence of these biases by comparing three sampling strategies: Random sampling, Roadside sampling, and Transect sampling – a spatially constrained variant of Roadside sampling. In these three strategies, non-cropland data are randomly distributed as they can be photo-interpreted. Based on reference maps at 30 m in four study sites, we followed a Monte Carlo approach to generate multiple realizations of each sampling strategy for ten sample sizes. The effect of the sampling strategy was then assessed in terms of representativeness of the data set collected and accuracy of the resulting maps. Results showed that data sets obtained from Roadside sampling were significantly less representative than those obtained from Random sampling but the resulting maps were only marginally less accurate (2% difference). Transect sampling captured systematically less variability than Random or Roadside sampling which led to differences in accuracy as large as 15%. The effect of sample size on accuracy varied across sites but generally leveled off after reaching 3000 pixels. Augmenting the size of Transect samples improved the classification accuracy but not sufficiently to match the performance of the other sampling strategies. Finally, we found that Random and Roadside training sets with similar representativeness yield comparable accuracy. Therefore, we conclude that roadside sampling can be a viable source of training data for cropland mapping if the range of environmental and management gradients is surveyed. This underlines the importance of survey planning to identify those routes that capture most variability.

ACS Style

François Waldner; Nicolas Bellemans; Zvi Hochman; Terence Newby; Diego de Abelleyra; Santiago R. Verón; Sergey Bartalev; Mykola Lavreniuk; Nataliia Kussul; Guerric Le Maire; Margareth Simoes; Sergii Skakun; Pierre Defourny. Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed. International Journal of Applied Earth Observation and Geoinformation 2019, 80, 82 -93.

AMA Style

François Waldner, Nicolas Bellemans, Zvi Hochman, Terence Newby, Diego de Abelleyra, Santiago R. Verón, Sergey Bartalev, Mykola Lavreniuk, Nataliia Kussul, Guerric Le Maire, Margareth Simoes, Sergii Skakun, Pierre Defourny. Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed. International Journal of Applied Earth Observation and Geoinformation. 2019; 80 ():82-93.

Chicago/Turabian Style

François Waldner; Nicolas Bellemans; Zvi Hochman; Terence Newby; Diego de Abelleyra; Santiago R. Verón; Sergey Bartalev; Mykola Lavreniuk; Nataliia Kussul; Guerric Le Maire; Margareth Simoes; Sergii Skakun; Pierre Defourny. 2019. "Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed." International Journal of Applied Earth Observation and Geoinformation 80, no. : 82-93.

Research article
Published: 25 January 2019 in Agronomy for Sustainable Development
Reads 0
Downloads 0

Achieving sustainable global food security for a rapidly growing world population is one of the greatest challenges of our time. Producing more food efficiently by closing the yield gaps is regarded as a promising solution to address this challenge without further expanding farming land. However, there is limited understanding of the causes contributing to yield gaps. The present study aimed to comprehensively examine three dimensions of the causes for the wheat yield gaps in Australia: farm management practices, farm characteristics and grower characteristics. Computer-assisted telephone interviews of 232 wheat producers from 14 contrasting local areas were conducted. The data collected on these three dimensions were used to develop a comprehensive framework to understand causes of yield gaps. Results reveal significant differences between farms with smaller yield gaps and those with greater yield gaps in relation to farming management as well as farm and grower characteristics. Findings further underline that farms with smaller yield gaps are likely to be smaller holdings growing less wheat on more favourable soil types, are more likely to apply more N fertiliser, to have a greater crop diversity, to soil-test a greater proportion of their fields, to have fewer resistant weeds, to adopt new technologies, and are less likely to grow wheat following either cereal crops or a pasture. They are more likely to use and trust a fee-for-service agronomist, and have a university education. The dynamic relationships between grower characteristics and farm management practices in causing yield gaps are further highlighted through a path analysis. This study is the first to demonstrate that yield gaps are the result of the intertwined dynamics between biophysical factors, grower socio-psychological characteristics and farm management practices. Socio-psychological factors not only directly contribute to yield gaps, but they also influence farm management practices that in turn contribute to yield gaps. Our findings suggest that, to close wheat yield gaps, it is important to develop integrated strategies that address both socio-psychological and farm management dimensions.

ACS Style

Airong Zhang; Zvi Hochman; Heidi Horan; Javier Garcia Navarro; Bianca Das; Francois Waldner. Socio-psychological and management drivers explain farm level wheat yield gaps in Australia. Agronomy for Sustainable Development 2019, 39, 10 .

AMA Style

Airong Zhang, Zvi Hochman, Heidi Horan, Javier Garcia Navarro, Bianca Das, Francois Waldner. Socio-psychological and management drivers explain farm level wheat yield gaps in Australia. Agronomy for Sustainable Development. 2019; 39 (1):10.

Chicago/Turabian Style

Airong Zhang; Zvi Hochman; Heidi Horan; Javier Garcia Navarro; Bianca Das; Francois Waldner. 2019. "Socio-psychological and management drivers explain farm level wheat yield gaps in Australia." Agronomy for Sustainable Development 39, no. 1: 10.