Accounting for training data error in machine learning applied to earth observations

A Elmes, H Alemohammad, R Avery, K Caylor… - Remote Sensing, 2020 - mdpi.com
Remote sensing, or Earth Observation (EO), is increasingly used to understand Earth system
dynamics and create continuous and categorical maps of biophysical properties and land …

Crop type map** without field-level labels: Random forest transfer and unsupervised clustering techniques

S Wang, G Azzari, DB Lobell - Remote sensing of environment, 2019 - Elsevier
Crop type map** at the field level is necessary for a variety of applications in agricultural
monitoring and food security. As remote sensing imagery continues to increase in spatial …

Better data, higher impact: improving agricultural data systems for societal change

C Carletto - European Review of Agricultural Economics, 2021 - academic.oup.com
The agricultural sector is undergoing a period of rapid transformation, driven by the powerful
and interconnected impacts of climate change, demographic transitions and uneven …

Satellite-based assessment of yield variation and its determinants in smallholder African systems

M Burke, DB Lobell - Proceedings of the National Academy of Sciences, 2017 - pnas.org
The emergence of satellite sensors that can routinely observe millions of individual
smallholder farms raises possibilities for monitoring and understanding agricultural …

New perspectives on farm size and productivity

NE Rada, KO Fuglie - Food Policy, 2019 - Elsevier
The farm size and productivity debate has been limited by the focus on land or labor
productivity, generally showing respective productivity advantages to smaller or larger sized …

Land productivity and plot size: Is measurement error driving the inverse relationship?

S Desiere, D Jolliffe - Journal of Development Economics, 2018 - Elsevier
This paper revisits the decades-old puzzle of the inverse plot-size productivity relationship
(IR), which states that land productivity decreases as plot size increases. While existing …

A new attention-based CNN approach for crop map** using time series Sentinel-2 images

Y Wang, Z Zhang, L Feng, Y Ma, Q Du - Computers and electronics in …, 2021 - Elsevier
Accurate crop map** is of great importance for agricultural applications, and deep
learning methods have been applied on multi-temporal remotely sensed images to classify …

Revisiting the farm size‐productivity relationship based on a relatively wide range of farm sizes: Evidence from Kenya

M Muyanga, TS Jayne - American Journal of Agricultural …, 2019 - Wiley Online Library
This paper revisits the inverse farm size‐productivity relationship in Kenya. The study makes
two contributions. First, the relationship is examined over a much wider range of farm sizes …

Heterogeneity, measurement error, and misallocation: Evidence from African agriculture

D Gollin, C Udry - Journal of Political Economy, 2021 - journals.uchicago.edu
Standard measures of productivity display enormous dispersion across farms in Africa. Crop
yields and input intensities appear to vary greatly, seemingly in conflict with a model of …

To specialize or diversify: agricultural diversity and poverty dynamics in Ethiopia

JD Michler, AL Josephson - World Development, 2017 - Elsevier
Recent agricultural development policies have begun to shift focus from the promotion of a
few staple crops toward encouraging crop diversity. The belief is that crop diversification is …