Forecast Report with Analog Years-Kenya

Introduction

This is a protype forecast report. The goal is to assist users in evaluating current forecasts in the context of past forecasts.

The report includes the following key components:

1. Mean Area, Production, and Yield over the years 2006 to 2016:This provides context for interpreting the grain data

2. Historical Out of Sample Forecast Error Averaged Over a 10 Year+ Period. We show the Mean Absolute Percent Error (MAPE).

3. Yield Forecast, (based on May 2021 Precip, NDVI, Et0 ) expressed as percent of mean yield over the period 2006 - 2016.

4. Forecasts and Forecast Error in Analog Years We show specific forecasts and forecast error for years were climatologically similar to those in this report.

Summary Figures

Mean area, production, and yields for the years 2006 to 2016.

---

---

Out of Sample Forecast Error (MAPE)

Mean Absolute Percent Error (MAPE) calculated based on out of sample seasonfal forecasts conducted over 2001-2014. Lower scores indicate greater accuracy. Forecasts are based on model type MODEL¹

---

---

Yield Forecast for May 2021

Forecast values expressed as percent of Mean Yields over the Years 2006 - 2016.

The figure shows predicted percent of mean (center) as well as lower (left) and higher (right) predicted percent of mean intervals.

---

---

Static and Dynamic Version of Main Forecast

Roll over the polygon borders to get the district name and % of mean forecast value.

Static Version

This map shows the main % of mean forecast value along with district lables for reference.

This table shows the forecast percentage of mean values in the above table along with the mean yield values from the first figure.

---

Table of Mean Yields and Predicted Percent of Mean Values

District	% of mean	% of mean (low)	% of mean (high)
Mombasa	0.91	0.56	1.25
Kwale	1.32	1.01	1.62
Kilifi	1.06	0.82	1.31
Tana River	0.66	0.58	0.74
Lamu	0.89	0.71	1.06
Taita Taveta	0.29	-0.05	0.64
Meru	0.95	0.63	1.27
Tharaka Nithi	0.77	0.66	0.89
Embu	1.23	1.23	1.23
Kitui	1.01	0.48	1.54
Machakos	0.43	0.13	0.74
Makueni	2.68	1.54	3.81
Nyandarua	0.67	0.47	0.87
Nyeri	1.17	1.14	1.21
Kirinyaga	0.49	0.17	0.80
Murang'a	0.50	0.15	0.84
Kiambu	0.51	0.27	0.74
West Pokot	0.81	0.56	1.06
Samburu	1.35	1.07	1.63
Trans Nzoia	0.99	0.91	1.06
Uasin Gishu	0.88	0.86	0.90
Elgeyo-Marakwet	1.23	1.11	1.34
Nandi	1.16	0.98	1.34
Baringo	0.98	0.68	1.27
Laikipia	0.91	0.63	1.19
Nakuru	0.78	0.41	1.14
Narok	1.11	0.87	1.34
Kajiado	0.94	0.46	1.41
Kericho	1.31	1.22	1.40
Bomet	1.32	1.05	1.59
Kakamega	0.98	0.54	1.42
Vihiga	1.14	0.97	1.30
Bungoma	0.69	0.65	0.73
Busia	1.16	0.98	1.34
Siaya	0.92	0.62	1.23
Kisumu	1.15	0.81	1.48
Homa Bay	0.56	0.28	0.85
Migori	1.00	0.84	1.16
Kisii	0.79	0.48	1.11
Nyamira	0.84	0.41	1.27

---

Analog Year Forecasts

Yield forecasts in analog years. <–DESCRIPTION OF ANALOG YEAR PROCESS–>.
***

---

Analog Year Forecasts Errors

Forecast errors in analog years. If observed data is not available in a given year we cannot calculate forecast errors. Values are expressed a percentage of observed yields in a given year (t):

---

\[\frac{(observed_{(t)}-forecast_{(t)})}{observed_{(t)}}\] ***

Positive (+) values indicate an under prediction. Negative (-) values indicate an over prediction.

---

---

1. Extra/Extended Trees. A type of Random Forest Model↩︎